diff --git a/01 -  Clean Images.ipynb b/01 -  Clean Images.ipynb
index c81cbf41..6c8e5ff6 100644
--- a/01 -  Clean Images.ipynb	
+++ b/01 -  Clean Images.ipynb	
@@ -74,7 +74,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,
diff --git a/02 - Image_Preparation.ipynb b/02 - Image_Preparation.ipynb
index 5e80137b..fe540e81 100644
--- a/02 - Image_Preparation.ipynb	
+++ b/02 - Image_Preparation.ipynb	
@@ -60,21 +60,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0 data_raw_all\\0.0_0.0.jpg\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\Muell\\AppData\\Local\\Temp\\ipykernel_12520\\403455051.py:14: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.NEAREST or Dither.NONE instead.\n",
-      "  test_image = test_image.resize((target_size_x, target_size_y), Image.NEAREST)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "0 data_raw_all\\0.0_0.0.jpg\n",
       "500 data_raw_all\\2.6_35a8c7850fdd0293ac7a2b8e7fa354b9.jpg\n",
       "1000 data_raw_all\\5.4_main_ana3_20221213-134708.jpg\n",
       "1500 data_raw_all\\8.5_4211_analog1_20200816-075704.jpg\n"
@@ -147,7 +133,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.11.8"
   },
   "vscode": {
    "interpreter": {
diff --git a/03 - Train_CNN_Analog-Readout_Version-Small2.ipynb b/03 - Train_CNN_Analog-Readout_Version-Small2.ipynb
index 2442244a..abd35f49 100644
--- a/03 - Train_CNN_Analog-Readout_Version-Small2.ipynb	
+++ b/03 - Train_CNN_Analog-Readout_Version-Small2.ipynb	
@@ -31,6 +31,8 @@
     "\n",
     "##########################################################################\n",
     "\n",
+    "## 2024-03-30: Code adapted to TF 2.16####################################\n",
+    "\n",
     "\n",
     "\n",
     "import os\n",
@@ -150,47 +152,123 @@
    },
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Model: \"model\"\n",
-      "_________________________________________________________________\n",
-      " Layer (type)                Output Shape              Param #   \n",
-      "=================================================================\n",
-      " input_1 (InputLayer)        [(None, 32, 32, 3)]       0         \n",
-      "                                                                 \n",
-      " batch_normalization (BatchN  (None, 32, 32, 3)        12        \n",
-      " ormalization)                                                   \n",
-      "                                                                 \n",
-      " conv2d (Conv2D)             (None, 32, 32, 32)        2432      \n",
-      "                                                                 \n",
-      " max_pooling2d (MaxPooling2D  (None, 8, 8, 32)         0         \n",
-      " )                                                               \n",
-      "                                                                 \n",
-      " conv2d_1 (Conv2D)           (None, 8, 8, 16)          12816     \n",
-      "                                                                 \n",
-      " max_pooling2d_1 (MaxPooling  (None, 4, 4, 16)         0         \n",
-      " 2D)                                                             \n",
-      "                                                                 \n",
-      " conv2d_2 (Conv2D)           (None, 4, 4, 32)          4640      \n",
-      "                                                                 \n",
-      " max_pooling2d_2 (MaxPooling  (None, 2, 2, 32)         0         \n",
-      " 2D)                                                             \n",
-      "                                                                 \n",
-      " flatten (Flatten)           (None, 128)               0         \n",
-      "                                                                 \n",
-      " dense (Dense)               (None, 128)               16512     \n",
-      "                                                                 \n",
-      " dense_1 (Dense)             (None, 64)                8256      \n",
-      "                                                                 \n",
-      " dense_2 (Dense)             (None, 2)                 130       \n",
-      "                                                                 \n",
-      "=================================================================\n",
-      "Total params: 44,798\n",
-      "Trainable params: 44,792\n",
-      "Non-trainable params: 6\n",
-      "_________________________________________________________________\n"
-     ]
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional_1\"</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1mModel: \"functional_1\"\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ input_layer (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)      │            <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span> │\n",
+       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,432</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>)       │        <span style=\"color: #00af00; text-decoration-color: #00af00\">12,816</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)       │         <span style=\"color: #00af00; text-decoration-color: #00af00\">4,640</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">8,256</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">130</span> │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ input_layer (\u001b[38;5;33mInputLayer\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m3\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m3\u001b[0m)      │            \u001b[38;5;34m12\u001b[0m │\n",
+       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │         \u001b[38;5;34m2,432\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m32\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m16\u001b[0m)       │        \u001b[38;5;34m12,816\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m16\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m32\u001b[0m)       │         \u001b[38;5;34m4,640\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m32\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m16,512\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │         \u001b[38;5;34m8,256\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m)              │           \u001b[38;5;34m130\u001b[0m │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">44,798</span> (174.99 KB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m44,798\u001b[0m (174.99 KB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">44,792</span> (174.97 KB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m44,792\u001b[0m (174.97 KB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">6</span> (24.00 B)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m6\u001b[0m (24.00 B)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [
@@ -243,80 +321,81 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch 1/30\n"
+      "Epoch 1/30\n",
+      "\u001b[1m 41/218\u001b[0m \u001b[32m━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - accuracy: 0.5233 - loss: 0.5301"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "C:\\Users\\Muell\\AppData\\Local\\Temp\\ipykernel_6032\\3831122756.py:11: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n",
-      "  history = model.fit_generator(train_iterator, validation_data = validation_iterator, epochs = Epoch_Anz)\n"
+      "C:\\Users\\Muell\\anaconda3\\envs\\py311-tf216-opencv\\Lib\\site-packages\\keras\\src\\trainers\\data_adapters\\py_dataset_adapter.py:120: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
+      "  self._warn_if_super_not_called()\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "218/218 [==============================] - 2s 6ms/step - loss: 0.4270 - accuracy: 0.6297 - val_loss: 0.2545 - val_accuracy: 0.7816\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 4ms/step - accuracy: 0.5383 - loss: 0.5049 - val_accuracy: 0.6897 - val_loss: 0.3257\n",
       "Epoch 2/30\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.1868 - accuracy: 0.8562 - val_loss: 0.1160 - val_accuracy: 0.8966\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.7489 - loss: 0.2985 - val_accuracy: 0.8966 - val_loss: 0.1359\n",
       "Epoch 3/30\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0925 - accuracy: 0.9183 - val_loss: 0.0570 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.8915 - loss: 0.1226 - val_accuracy: 0.9080 - val_loss: 0.0622\n",
       "Epoch 4/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0598 - accuracy: 0.9425 - val_loss: 0.0403 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9096 - loss: 0.0742 - val_accuracy: 0.9425 - val_loss: 0.0622\n",
       "Epoch 5/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0427 - accuracy: 0.9511 - val_loss: 0.0596 - val_accuracy: 0.9310\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9418 - loss: 0.0473 - val_accuracy: 0.9540 - val_loss: 0.0217\n",
       "Epoch 6/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0325 - accuracy: 0.9494 - val_loss: 0.0203 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9489 - loss: 0.0374 - val_accuracy: 0.9540 - val_loss: 0.0322\n",
       "Epoch 7/30\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0256 - accuracy: 0.9528 - val_loss: 0.0172 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9555 - loss: 0.0240 - val_accuracy: 0.8966 - val_loss: 0.0922\n",
       "Epoch 8/30\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0234 - accuracy: 0.9551 - val_loss: 0.0212 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9425 - loss: 0.0249 - val_accuracy: 0.9655 - val_loss: 0.0129\n",
       "Epoch 9/30\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0180 - accuracy: 0.9695 - val_loss: 0.0108 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9738 - loss: 0.0149 - val_accuracy: 0.9540 - val_loss: 0.0141\n",
       "Epoch 10/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0169 - accuracy: 0.9666 - val_loss: 0.0296 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9691 - loss: 0.0136 - val_accuracy: 0.9655 - val_loss: 0.0082\n",
       "Epoch 11/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0151 - accuracy: 0.9724 - val_loss: 0.0133 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9582 - loss: 0.0120 - val_accuracy: 0.9655 - val_loss: 0.0170\n",
       "Epoch 12/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0137 - accuracy: 0.9666 - val_loss: 0.0139 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9724 - loss: 0.0128 - val_accuracy: 0.9655 - val_loss: 0.0102\n",
       "Epoch 13/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0119 - accuracy: 0.9707 - val_loss: 0.0148 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9818 - loss: 0.0092 - val_accuracy: 0.9655 - val_loss: 0.0081\n",
       "Epoch 14/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0100 - accuracy: 0.9718 - val_loss: 0.0121 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9732 - loss: 0.0078 - val_accuracy: 0.9885 - val_loss: 0.0061\n",
       "Epoch 15/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0101 - accuracy: 0.9689 - val_loss: 0.0098 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9774 - loss: 0.0094 - val_accuracy: 0.9770 - val_loss: 0.0093\n",
       "Epoch 16/30\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0100 - accuracy: 0.9707 - val_loss: 0.0128 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9802 - loss: 0.0069 - val_accuracy: 0.9655 - val_loss: 0.0125\n",
       "Epoch 17/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0090 - accuracy: 0.9758 - val_loss: 0.0069 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9826 - loss: 0.0073 - val_accuracy: 0.9885 - val_loss: 0.0052\n",
       "Epoch 18/30\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0082 - accuracy: 0.9776 - val_loss: 0.0047 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9811 - loss: 0.0050 - val_accuracy: 0.9770 - val_loss: 0.0078\n",
       "Epoch 19/30\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0076 - accuracy: 0.9770 - val_loss: 0.0070 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9776 - loss: 0.0056 - val_accuracy: 0.9885 - val_loss: 0.0068\n",
       "Epoch 20/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0077 - accuracy: 0.9770 - val_loss: 0.0062 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9776 - loss: 0.0054 - val_accuracy: 0.9885 - val_loss: 0.0051\n",
       "Epoch 21/30\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0066 - accuracy: 0.9799 - val_loss: 0.0061 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9744 - loss: 0.0057 - val_accuracy: 0.9770 - val_loss: 0.0094\n",
       "Epoch 22/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0075 - accuracy: 0.9804 - val_loss: 0.0046 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9875 - loss: 0.0043 - val_accuracy: 0.9770 - val_loss: 0.0031\n",
       "Epoch 23/30\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0058 - accuracy: 0.9793 - val_loss: 0.0060 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9808 - loss: 0.0050 - val_accuracy: 0.9885 - val_loss: 0.0057\n",
       "Epoch 24/30\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0066 - accuracy: 0.9799 - val_loss: 0.0038 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9806 - loss: 0.0038 - val_accuracy: 0.9655 - val_loss: 0.0025\n",
       "Epoch 25/30\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0051 - accuracy: 0.9776 - val_loss: 0.0049 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9875 - loss: 0.0037 - val_accuracy: 0.9770 - val_loss: 0.0047\n",
       "Epoch 26/30\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0063 - accuracy: 0.9770 - val_loss: 0.0037 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9866 - loss: 0.0038 - val_accuracy: 0.9770 - val_loss: 0.0028\n",
       "Epoch 27/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0047 - accuracy: 0.9816 - val_loss: 0.0053 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9822 - loss: 0.0036 - val_accuracy: 0.9770 - val_loss: 0.0029\n",
       "Epoch 28/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0046 - accuracy: 0.9799 - val_loss: 0.0046 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9846 - loss: 0.0039 - val_accuracy: 1.0000 - val_loss: 0.0034\n",
       "Epoch 29/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0047 - accuracy: 0.9827 - val_loss: 0.0073 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9833 - loss: 0.0033 - val_accuracy: 1.0000 - val_loss: 0.0037\n",
       "Epoch 30/30\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0050 - accuracy: 0.9793 - val_loss: 0.0030 - val_accuracy: 0.9885\n"
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9810 - loss: 0.0036 - val_accuracy: 1.0000 - val_loss: 0.0030\n"
      ]
     }
    ],
@@ -331,10 +410,10 @@
     "if (Training_Percentage > 0):\n",
     "    train_iterator = datagen.flow(x_data, y_data, batch_size=Batch_Size)\n",
     "    validation_iterator = datagen.flow(X_test, y_test, batch_size=Batch_Size)\n",
-    "    history = model.fit_generator(train_iterator, validation_data = validation_iterator, epochs = Epoch_Anz)\n",
+    "    history = model.fit(train_iterator, validation_data = validation_iterator, epochs = Epoch_Anz)\n",
     "else:\n",
     "    train_iterator = datagen.flow(x_data, y_data, batch_size=Batch_Size)\n",
-    "    history = model.fit_generator(train_iterator, epochs = Epoch_Anz)\n",
+    "    history = model.fit(train_iterator, epochs = Epoch_Anz)\n",
     "\n"
    ]
   },
@@ -354,7 +433,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkQAAAHHCAYAAABeLEexAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB3GElEQVR4nO3dd3xT9f7H8VeSNt2D0kILLbPsUfZGpoIiuLdecIu4f17ndXvFfV1VcOLALSqKCIIMQfbeUFbZZXXTlZzfH6ctVErpSJu0fT8fjzyaJifnfBKjffudFsMwDERERERqMau7CxARERFxNwUiERERqfUUiERERKTWUyASERGRWk+BSERERGo9BSIRERGp9RSIREREpNZTIBIREZFaT4FIREREaj0FIhGpUXbt2oXFYmHSpEllfu3cuXOxWCzMnTu3xOMmTZqExWJh165d5apRRDyPApGIiIjUegpEIiIiUuspEImIiEitp0AkIi719NNPY7FY2Lp1K9dffz0hISFERETwxBNPYBgGe/bs4aKLLiI4OJjIyEhee+21086RlJTEzTffTP369fH19SUuLo5PP/30tOOSk5MZM2YMISEhhIaGMnr0aJKTk4uta/PmzVx++eWEhYXh6+tLt27dmDp1qkvf+7vvvku7du3w8fGhQYMGjBs37rR6tm3bxmWXXUZkZCS+vr5ER0dz9dVXk5KSUnjMH3/8Qb9+/QgNDSUwMJBWrVrx2GOPubRWESnKy90FiEjNdNVVV9GmTRtefPFFpk2bxvPPP09YWBgTJ05k8ODBvPTSS0yePJkHH3yQ7t27c8455wBw4sQJBg4cSEJCAnfddRdNmzblu+++Y8yYMSQnJ3PvvfcCYBgGF110EQsWLOCOO+6gTZs2/Pjjj4wePfq0WjZs2EDfvn1p2LAhjzzyCAEBAXz77bdcfPHF/PDDD1xyySUVfr9PP/00zzzzDEOHDmXs2LFs2bKF9957j2XLlrFw4UK8vb3Jyclh2LBhZGdnc/fddxMZGcm+ffv49ddfSU5OJiQkhA0bNnDhhRfSsWNHnn32WXx8fEhISGDhwoUVrlFESmCIiLjQU089ZQDGbbfdVvhYXl6eER0dbVgsFuPFF18sfPz48eOGn5+fMXr06MLH3njjDQMwvvjii8LHcnJyjN69exuBgYFGamqqYRiG8dNPPxmA8fLLLxe5Tv/+/Q3A+OSTTwofHzJkiNGhQwcjKyur8DGn02n06dPHaNGiReFjc+bMMQBjzpw5Jb7HTz75xACMnTt3GoZhGElJSYbdbjfOO+88w+FwFB73zjvvGIDx8ccfG4ZhGKtWrTIA47vvvjvjuf/3v/8ZgHH48OESaxAR11KXmYhUiltuuaXwvs1mo1u3bhiGwc0331z4eGhoKK1atWLHjh2Fj/32229ERkZyzTXXFD7m7e3NPffcQ3p6OvPmzSs8zsvLi7Fjxxa5zt13312kjmPHjvHnn39y5ZVXkpaWxpEjRzhy5AhHjx5l2LBhbNu2jX379lXovc6aNYucnBzuu+8+rNaT/1m99dZbCQ4OZtq0aQCEhIQAMGPGDDIzM4s9V2hoKAA///wzTqezQnWJSOkpEIlIpWjUqFGR30NCQvD19SU8PPy0x48fP174++7du2nRokWRYAHQpk2bwucLfkZFRREYGFjkuFatWhX5PSEhAcMweOKJJ4iIiChye+qppwBzzFJFFNT0z2vb7XaaNWtW+HzTpk154IEH+PDDDwkPD2fYsGHEx8cXGT901VVX0bdvX2655Rbq16/P1VdfzbfffqtwJFLJNIZIRCqFzWYr1WNgjgeqLAVB4sEHH2TYsGHFHhMbG1tp1/+n1157jTFjxvDzzz8zc+ZM7rnnHsaPH8/ixYuJjo7Gz8+P+fPnM2fOHKZNm8bvv//ON998w+DBg5k5c+YZP0MRqRi1EImIR2ncuDHbtm07rUVk8+bNhc8X/Dxw4ADp6elFjtuyZUuR35s1awaY3W5Dhw4t9hYUFFThmou7dk5ODjt37ix8vkCHDh34z3/+w/z58/nrr7/Yt28fEyZMKHzearUyZMgQXn/9dTZu3Mh///tf/vzzT+bMmVOhOkXkzBSIRMSjXHDBBRw8eJBvvvmm8LG8vDzefvttAgMDGTBgQOFxeXl5vPfee4XHORwO3n777SLnq1evHgMHDmTixIkcOHDgtOsdPny4wjUPHToUu93OW2+9VaS166OPPiIlJYURI0YAkJqaSl5eXpHXdujQAavVSnZ2NmCOefqnTp06ARQeIyKupy4zEfEot912GxMnTmTMmDGsWLGCJk2a8P3337Nw4ULeeOONwtackSNH0rdvXx555BF27dpF27ZtmTJlSpHxOAXi4+Pp168fHTp04NZbb6VZs2YcOnSIRYsWsXfvXtasWVOhmiMiInj00Ud55plnGD58OKNGjWLLli28++67dO/eneuvvx6AP//8k7vuuosrrriCli1bkpeXx+eff47NZuOyyy4D4Nlnn2X+/PmMGDGCxo0bk5SUxLvvvkt0dDT9+vWrUJ0icmYKRCLiUfz8/Jg7dy6PPPIIn376KampqbRq1YpPPvmEMWPGFB5ntVqZOnUq9913H1988QUWi4VRo0bx2muv0blz5yLnbNu2LcuXL+eZZ55h0qRJHD16lHr16tG5c2eefPJJl9T99NNPExERwTvvvMP9999PWFgYt912Gy+88ALe3t4AxMXFMWzYMH755Rf27duHv78/cXFxTJ8+nV69egEwatQodu3axccff8yRI0cIDw9nwIABPPPMM4Wz1ETE9SxGZY5mFBEREakGNIZIREREaj0FIhEREan1FIhERESk1lMgEhERkVpPgUhERERqPQUiERERqfW0DlEJnE4n+/fvJygoCIvF4u5yREREpBQMwyAtLY0GDRqctlH0mSgQlWD//v3ExMS4uwwREREphz179hAdHV2qYxWISlCwRcCePXsIDg52czUiIiJSGqmpqcTExJRp42YFohIUdJMFBwcrEImIiFQzZRnuokHVIiIiUuspEImIiEitp0AkIiIitZ7GEBUjPj6e+Ph4HA5HqY53OBzk5uZWclU1k7e3Nzabzd1liIhILWcxDMNwdxGeKjU1lZCQEFJSUoodVG0YBgcPHiQ5Obnqi6tBQkNDiYyM1FpPIiLiEmf7+10ctRBVQEEYqlevHv7+/vqDXkaGYZCZmUlSUhIAUVFRbq5IRERqKwWicnI4HIVhqG7duu4up9ry8/MDICkpiXr16qn7TERE3EKDqsupYMyQv7+/myup/go+Q43DEhERd1EgqiB1k1WcPkMREXE3BSIRERGp9RSIpEKaNGnCG2+84e4yREREKkSDqmuhgQMH0qlTJ5cEmWXLlhEQEFDxokRERNxIgchdnA7IywK754UJwzBwOBx4eZ396xEREVEFFYmIiFQudZm5Q14WHFwHRxPAcFbppceMGcO8efN48803sVgsWCwWJk2ahMViYfr06XTt2hUfHx8WLFjA9u3bueiii6hfvz6BgYF0796dWbNmFTnfP7vMLBYLH374IZdccgn+/v60aNGCqVOnVul7FBERKSsFIhcyDIPMnLyz3xw2Mh0W8356aulec5ZbaRccf/PNN+nduze33norBw4c4MCBA8TExADwyCOP8OKLL7Jp0yY6duxIeno6F1xwAbNnz2bVqlUMHz6ckSNHkpiYWOI1nnnmGa688krWrl3LBRdcwHXXXcexY8cq/PmKiIhUFnWZudCJXAdtn5xRxlcddMm1Nz47DH/72f9xhoSEYLfb8ff3JzIyEoDNmzcD8Oyzz3LuuecWHhsWFkZcXFzh78899xw//vgjU6dO5a677jrjNcaMGcM111wDwAsvvMBbb73F0qVLGT58eLnem4iISGVTC5EU6tatW5Hf09PTefDBB2nTpg2hoaEEBgayadOms7YQdezYsfB+QEAAwcHBhdtziIiIeCK1ELmQn7eNjc8OK93BjlxI2mjer9cWbN4VvnZF/XO22IMPPsgff/zBq6++SmxsLH5+flx++eXk5OSUeB5v76LvxWKx4HRW7VgpERGRslAgKkZ8fDzx8fE4HI4yvc5isZSq28rkBX4BkHcCjBNg9yt7oeVkt9tL9d4WLlzImDFjuOSSSwCzxWjXrl2VXJ2IiEjVU5dZMcaNG8fGjRtZtmxZ5V7IN8j8mZ1Wudf5hyZNmrBkyRJ27drFkSNHzth606JFC6ZMmcLq1atZs2YN1157rVp6RESkRlIgciefYPNndiqUcpaYKzz44IPYbDbatm1LRETEGccEvf7669SpU4c+ffowcuRIhg0bRpcuXaqsThERkapiMUo7X7sWSk1NJSQkhJSUFIKDg4s8l5WVxc6dO2natCm+vr7lu4DhNNcjMpwQ0Qq8/V1QdfXjks9SREQkX0l/v89ELUTuZLGCPdC8n1W13WYiIiJykgKRu53abSYiIiJuoUDkbj75A6tzMsz9zURERKTKKRC5m5cP2OyAATnp7q5GRESkVlIgcjeL5WQrURVPvxcRERGTApEnKBhHlKVxRCIiIu6gQOQJfPJnmjmyIS/bvbWIiIjUQgpEnsDqBd75+4ip20xERKTKKRB5Cl9NvxcREXEXBSJPUTiwOr1Kt/GoLJMmTSI0NNTdZYiIiJSKApGn8PYHiw0Mh7kmkYiIiFQZBSJPoen3IiIibqNA5EmqcBsPp9PJ+PHjadq0KX5+fsTFxfH999/jdDqJjo7mvffeK3L8qlWrsFqt7N69G4DXX3+dDh06EBAQQExMDHfeeSfp6VpYUkREqicvdxdQoxgG5GaW//UWK+SeMG8nUsBWhn883v5mK1MpjR8/ni+++IIJEybQokUL5s+fz/XXX8+MGTO45ppr+PLLLxk7dmzh8ZMnT6Zv3740btwYAKvVyltvvUXTpk3ZsWMHd955Jw899BDvvvtu6WsWERHxEApErpSbCS80cM+1H9sP9oBSHZqdnc0LL7zArFmz6N27NwDNmjVjwYIFTJw4kYceeojXXnuNxMREGjVqhNPp5Ouvv+Y///lP4Tnuu+++wvtNmjTh+eef54477lAgEhGRakmBqBZKSEggMzOTc889t8jjOTk5dO7cmU6dOtGmTRu+/PJLHnnkEebNm0dSUhJXXHFF4bGzZs1i/PjxbN68mdTUVPLy8sjKyiIzMxN/f/+qfksiIiIVokBUjPj4eOLj43E4yrj7vLe/2VJTEVlpcHwHWL2hXpvSd4N5lz6EFIz1mTZtGg0bNizynI+PDwDXXXddYSD68ssvGT58OHXr1gVg165dXHjhhYwdO5b//ve/hIWFsWDBAm6++WZycnIUiEREpNpRICrGuHHjGDduHKmpqYSEhJT+hRZLqbutzsjLD9IPAgZYbeDtV7HzFaNt27b4+PiQmJjIgAEDij3m2muv5T//+Q8rVqzg+++/Z8KECYXPrVixAqfTyWuvvYbVao7L//bbb11ep4iISFVRIPI0Vqu5t1l2mnmrhEAUFBTEgw8+yP3334/T6aRfv36kpKSwcOFCgoODGT16NE2aNKFPnz7cfPPNOBwORo0aVfj62NhYcnNzefvttxk5ciQLFy4sEphERESqG02790SF6xFV3vT75557jieeeILx48fTpk0bhg8fzrRp02jatGnhMddddx1r1qzhkksuwc/vZDCLi4vj9ddf56WXXqJ9+/ZMnjyZ8ePHV1qtIiIilc1iGDVgn4hKUtBllpKSQnBwcJHnsrKy2LlzJ02bNsXX19e1F849AYc3AxaI7Gi2GtVglfpZiohIrVPS3+8zqdl/aasrL19zUDUG5GixQxERkcqmQOSJtI2HiIhIlVIg8lS+VbeNh4iISG2nQOSp7PktRHlZ4Mhxby0iIiI1nAJRBVVkTHqew3nmJ21eJxdbrOHdZhrXLyIi7qZAVE7e3t4AZGaWfTPX7DwHWw6msfVQeslhoGAcUVbNDkQFn2HBZyoiIlLVtDBjOdlsNkJDQ0lKSgLA398fSym32XAaBjnZWTgNg+Q0K372M/1j8IE8A9JTwO9EmXazrw4MwyAzM5OkpCRCQ0Ox2WzuLklERGopBaIKiIyMBCgMRWWRkp7DiVwHWce8CPY7Q8uIYUDqUTCckAJ42StQrecKDQ0t/CxFRETcQYGoAiwWC1FRUdSrV4/c3NwyvXbzugO8OmcLreoH8e71Xc984LR3Yedc6DEWetxcsYI9kLe3t1qGRETE7RSIXMBms5X5j3rfVlHc/8NG9qUlk5ZrISLIp/gDG3WGdZ9Dwi9wzjgXVCsiIiL/pEHVblIv2Jf2Dc21huZtPXzmA2OHmD/3LIWslCqoTEREpPZRIHKjwa3qATBncwljkOo0gbDmYDhg519VU5iIiEgto0DkRgNbm4Fo/rbD5Ja0JlFBK9H22VVQlYiISO2jQORGcdGhhAXYScvKY8Xu42c+sHl+IEqYbc48ExEREZdSIHIjm9XCgJYRAMzZUkK3WZN+YPWG5N1wbEcVVSciIlJ7KBC52aDWpRhH5BMIjXqZ9xPUbSYiIuJqCkRudk6LcKwW2Hoonb3HS9gGpPlg8+f2P6umMBERkVpEgcjNQv3tdG1cB4A5W0ox/X7XX5CXUwWViYiI1B4KRB5gYP70+7kldZvV7wABEZCTDnuWVFFlIiIitYMCkQcYnD+OaOH2I2TlOoo/yGo9pdtM44hERERcSYHIA7SODCIqxJesXCeLdxw984EFgUgDq0VERFxKgcgDWCyWwm6zEmebFQSig2shvYTjREREpEwUiIoRHx9P27Zt6d69e5Vds6DbbM6WwxhnWnwxsB5EdjDv75hbNYWJiIjUAgpExRg3bhwbN25k2bJlVXbNPs3rYrdZSTyWyfbDGWc+8NRVq0VERMQlFIg8RICPFz2bhQFn6TYr3NfsT3CWsP+ZiIiIlJoCkQcZVDCOqKRtPGJ6grc/ZCTBofVVVJmIiEjNpkDkQQrGES3deYy0rNziD/LygSb9zfuafi8iIuISCkQepEl4AE3DA8hzGixMOHLmA1uca/7c/FvVFCYiIlLDKRB5mIJusz9LGkfUeoT5c+9SSN1fBVWJiIjUbApEHmZQ6wjgLNPvgxuYY4kANv1aRZWJiIjUXApEHqZH0zD87TYOp2WzYX/qmQ9sM8r8ufHnqilMRESkBlMg8jA+Xjb6xoYDZ5l+32ak+TPxb0g/XAWViYiI1FwKRB6oYLbZnyVNv6/TGKI6geGEzeo2ExERqQgFIg80sJU5jmj1nmSOZeSc+cC2F5k/N02tgqpERERqLgUiDxQV4kebqGAMA+ZtLaGVqCAQ7ZwPmceqpjgREZEaSIHIQw3KbyWas7mE8UF1m0O9duDMgy3Tq6gyERGRmkeByEMVjCOat/UweY4S9ixrmz/bTN1mIiIi5aZA5KE6xYQS4udNyolcVu9JPvOBBd1m2/+ErBKm6YuIiMgZKRB5KC+blQEtzW6zEletjmgNdVuAIwe2zqii6kRERGoWBSIPduqq1WdksZzSbaZFGkVERMpDgciDDWhZD4sFNh1I5UDKiTMfWNBttm0W5GRUTXEiIiI1iAKRBwsLsNM5JhSAuSW1EkV2hNDGkHcCEmZVTXEiIiI1iAKRhxvUKn/V6pLGEZ3abaa9zURERMpMgcjDDcqffr8w4QjZeY4zH9gmv9ts6wzIzaqCykRERGoOBSIP165BMPWCfMjMcbB0ZwmrUTfsCsENIScddsypugJFRERqAAUiD2exWErXbWa1QpuR5v2NWqRRRESkLBSIqoGC6fclDqwGaJM/jmjLNMgrYVNYERERKUKBqBroGxuOt83CziMZ7DxSwrT6Rr0gIAKyUmDX/KorUEREpJpTIKoGgny96d4kDIA5JXab2dRtJiIiUg4KRNVEwWavc7aUEIjgZLfZ5mngyKvkqkRERGoGBaJqYmD+wOolO46RkV1C0GnSD/zqQOYRSPy7iqoTERGp3hSIqonmEQE0CvMnx+FkYcKRMx9o84ZWI8z76jYTEREpFQWiasKcfl+KzV7h5N5mm34Bp7OSKxMREan+FIiqkYJVq+duScIwjDMf2GwA+ARD+kHYu7SKqhMREam+FIiqkV7N6uLrbeVAShabD6ad+UAvH2g53LyvbjMREZGzUiCqRny9bfRtHg6cZdVqKNptVlJrkoiIiCgQVTcDT+k2K1HsEPAOgJRE2L+qCioTERGpvhSIqpmCgdUrdh8nObOE7Tm8/aDFueb9jT9XQWUiIiLVlwJRNRNdx5+W9QNxGjB/WwnT7wHa5i/SuGmqus1ERERKoEBUDRXMNpu18VDJB7Y4D7x84dgOOLShCioTERGpnhSIqqHz2kYC5r5m2XmOMx/oEwTNh5j3N2m2mYiIyJkoEFVDnWNCqR/sQ1p2Hn8nHC354IJuM40jEhEROSMFomrIarUwrJ3ZSvT7+oMlH9xyOFi94fBmOLy1CqoTERGpfhSIqqnh+YFo5saD5DlK2J7DLxSaDTTvb1IrkYiISHFqRSC65JJLqFOnDpdffrm7S3GZHk3DqOPvzfHMXJbuOlbywYXdZhpHJCIiUpxaEYjuvfdePvvsM3eX4VJeNivntq0PlKLbrNUIsNjg4Fo4trMKqhMREaleakUgGjhwIEFBQe4uw+XObx8FwIwNB3E6S1hnKKAuNOln3tdsMxERkdO4PRDNnz+fkSNH0qBBAywWCz/99NNpx8THx9OkSRN8fX3p2bMnS5dqB3eAPrF1CfTx4lBqNqv2JJd8sLrNREREzsjtgSgjI4O4uDji4+OLff6bb77hgQce4KmnnmLlypXExcUxbNgwkpJO7uXVqVMn2rdvf9pt//79VfU23MLHy8bg/EUaZ2w4S7dZ65GABfYth5S9lV+ciIhINeLl7gLOP/98zj///DM+//rrr3Prrbdy4403AjBhwgSmTZvGxx9/zCOPPALA6tWrXVJLdnY22dnZhb+npqa65LyV6fz2kUxds5/p6w/w6PmtsVgsxR8YVB8a9YLERbDpF+g1tmoLFRER8WBubyEqSU5ODitWrGDo0KGFj1mtVoYOHcqiRYtcfr3x48cTEhJSeIuJiXH5NVxtQKsIfL2t7Dl2go0HzhLg2l5k/lS3mYiISBEeHYiOHDmCw+Ggfv36RR6vX78+Bw+epYvoFEOHDuWKK67gt99+Izo6+oxh6tFHHyUlJaXwtmfPngrVXxX87V4MaBkBwIyzzTZrM9L8mbgI0s6yD5qIiEgt4tGByFVmzZrF4cOHyczMZO/evfTu3bvY43x8fAgODi5yqw6GtzcXaZx+tkAUEg0NuwIGbP618gsTERGpJjw6EIWHh2Oz2Th0qGhrxqFDh4iMjHRTVZ5ncOv6eNssbEtKJyEpveSD22hvMxERkX/y6EBkt9vp2rUrs2fPLnzM6XQye/bsM7by1EYhft70aR4OlGK2WcH0+10LIPVAJVcmIiJSPbg9EKWnp7N69erCmWI7d+5k9erVJCYmAvDAAw/wwQcf8Omnn7Jp0ybGjh1LRkZG4awzMZ3fvpSbvYY1g5heYDjgr9eqoDIRERHP5/ZAtHz5cjp37kznzp0BMwB17tyZJ598EoCrrrqKV199lSeffJJOnTqxevVqfv/999MGWtd2Q9vWx2qBdftS2HMss+SDBz9u/lwxCY7vquzSREREPJ7FMIwS9nyoneLj44mPj8fhcLB161ZSUlKqxQDrqyYuYsnOY/xnRBtu6d+s5IM/uxh2zIG4a+CSCVVSn4iISFVITU0lJCSkTH+/3d5C5InGjRvHxo0bWbZsmbtLKZOCbrOzjiMCGPKE+XPN15C0qRKrEhER8XwKRDXIsPxAtHz3cZLSsko+uGFXaH0hYMCc/1Z+cSIiIh5MgagGiQrxo1NMKIYBMzeUYuHFwU8AFnMrj30rKr0+ERERT6VAVMMML+1sM4B6rSHuavP+7OcqsSoRERHPpkBUwwxvZwaiRTuOkpyZc/YXDHwErN7mAOud8yu5OhEREc+kQFTDNAkPoHVkEA6nwR8bS9FtVqcJdB1j3p/9LGjSoYiI1EIKRDXQ+e2jgFLONgM450Hw8oO9y2Dr75VYmYiIiGdSICpGfHw8bdu2pXv37u4upVwKxhHN33aE9Oy8s78gKBJ63WHen/0cOJ2VWJ2IiIjnUSAqRnVdh6hAy/qBNA0PICfPyZzNSaV7UZ97wCcEkjbA+h8qt0AREREPo0BUA1kslpOzzUrbbeYfBn3vNu/P+S84ciupOhEREc+jQFRDFcw2m7M5iaxcR+le1HMsBETA8Z2w6vNKrE5ERMSzKBDVUB2jQ2gQ4ktmjoO/th0p3Yt8AqH/g+b9eS9D7onKK1BERMSDKBDVUBaLpXArj+nrD5T+hd1uhJAYSDsASz+opOpEREQ8iwJRDVYw/X7WxkPkOko5c8zLx1ysEWDB65CVWknViYiIeA4Fohqsa+M6hAfaSc3KY/GOo6V/YcerIbwlnDgOi+Irr0AREREPoUBUg9msFs5rV9BtVsrZZgA2Lxj0uHl/0TuQUcoxSCIiItWUAlExqvvCjKcqmG02c8MhHM4ybMvRZhRExUFOOiz4XyVVJyIi4hkUiIpR3RdmPFWvZnUJ9vXiSHo2K3YfL/0LrVYY/KR5f+kHkLKvcgoUERHxAApENZzdy8rQtvUB+L0s3WYAsUOgcV9wZMO8lyqhOhEREc+gQFQLFHSbzdhwEKMsu9lbLDAkv5Vo1RdwdHslVCciIuJ+CkS1wDktI/C329iXfIJ1+1LK9uJGvaDFMDAc5pYeIiIiNZACUS3g621jUKt6QDm6zQAG/8f8uf4HOLjOhZWJiIh4BgWiWqJws9f1Zew2A4jqCO0uNe//+byLKxMREXE/BaJaYlDreti9rOw4ksG2pPRynOBxsNhg6++QuNj1BYqIiLiRAlEtEejjxTktwgGYvq4c3WbhsdD5OvP+7GehrK1MIiIiHkyBqBYZlj/b7PcN5QhEAAMeBpsP7F4I2/8s1ykysvPYezyzfNcXERGpJApExahJK1Wfamib+tisFjYdSGX30YyynyAkGrrfYt6f/jDknijTy/McTq5+fzGDXp3LjsPl6LYTERGpJApExahJK1Wfqk6And7N6gLlnG0GcM6DEBgJR7fB7OfK9NLJSxJZty+FXIfBwgTtjyYiIp5DgaiWGda+gt1m/mEw6i3z/uJ3YdeCUr3sWEYOr83cUvj76j1lXA9JRESkEikQ1TLD2tbHYoFVicls3J9avpO0HAadbwAM+OlOyE4760tem7mF1Kw8/O02ANbsTS7ftUVERCqBAlEtUy/Yl/PzW4ke+mENeQ5n+U407AUIiYHk3TDziRIP3bA/hS+XJgLw2hVxAGw/nE5qVm75ri0iIuJiCkS10NOj2hHi5836falMnL+jfCfxDYaL4s37Kz6BhFnFHmYYBs9M3YhhwIUdozi/QxQxYX4YBqzbq24zERHxDApEtVC9IF+eGtkWgDdnbSMh6exdXsVqNgB63G7e//luOHH8tEN+WXuApbuO4ett5bEL2gAQFx0KwOo9yeW7roiIiIspENVSl3RuyKBWEeQ4nPz7+7U4nOVcaHHo0xDWHNL2w/RHijyVmZPHC9M2AXDnwFgahPoB0CkmFFAgEhERz6FAVEtZLBZeuLQDQT5erEpM5pOFO8t3Irs/XPweWKyw9mvY9EvhU+/N3c7B1Cyi6/hx2znNCh8/NRCVeV81ERGRSqBAVItFhfjx+AizG+uVGVvYeaQcizUCNOoJfe4x7/9yH2QcIfFoZuH4pP+MaIOvt63w8HYNQrBZLRxOy+ZgalZF3oKIiIhLKBDVcld1j6FfbDjZeU4e/n4tzvJ2nQ16DCLaQOYR+PU+/jttAzl5TvrG1i3cMqSAn91Gq/pBAKxRt5mIiHgABaJazmKxMP7SDvjbbSzddYzPF+8u34m8fOCSCWD1gk2/4LP5R2xWC0+NbIfFYjnt8E6NQgFYpUAkIiIeQIFIiAnz59HzWwPw0u+b2XOsnJuvNuiEo/+/AXjO+xPu7OJPy/yWoH/qlD/TTC1EIiLiCRSIilFTN3ctyXU9G9OzaRiZOQ4embK23IOdP7NdylpnU0IsmdyT+Tac4Txx+QOr1+1NKf8MNxERERdRICpGTd3ctSRWq4WXLuuIr7eVhQlH+WrpnjKf42h6Nq//uZP/yx2Lw2rHe8csWPlZscfG1gskwG4jI8dBQlJ6RcsXERGpEAUiKdQkPIAHz2sFwAu/bWJ/8okyvf7VmVtIy8rDHtUWy+D87TxmPAbHTx+XZLNa6BAdAqjbTERE3E+BSIq4sW9TujQKJT07j0enrCt119n6fSl8vcxsVXp6VDusfcZBTC/ISYefx4Hz9D3TCrrNVmujVxERcTMFIinCZrXw8uVx2L2szNt6mB9W7jvrawzD4OmpGzAMGBXXgO5NwsBqg4vfBW9/2PUXLH3/tNdpYLWIiHgKBSI5TWy9QO4f2hKAZ3/ZwKGzLJ44dc1+lu8+jp+3jUcvaH3yibrN4dxnzfuznoIj24q8rqCFaPPBNE7kOFxWv4iISFkpEEmxbu3flI7RIaRm5fH4j+vP2HWWkZ3HC7+Z+5WNG9ScqBC/ogd0uxmaDYS8LPhpLDjyCp+KCvGlXpAPDqfBhv0plfVWREREzkqBSIrlZbPy8uUd8bZZmLXpEFPX7C/2uHfnJnAoNZuYMD9u6d/s9AOsVhj1DvgEw95l8PdbhU9ZLJaT44jUbSYiIm6kQCRn1DoymLsGtQDg6akbOJKeXeT53Ucz+GC+uSnsEyPaFtmvrIjQGBj+onl/zgtwaEPhUwUbva7ZqxYiERFxHwUiKdGdg5rTJiqY45m5PPXzhiLPPT9tEzkOJ/1bhHNu2/oln6jTtdDyfHDmwo+3Q54ZrjoVthAdr4zyRURESkWBSErkbbPyyuUdsVktTFt3gOnrDgAwb+th/th4CC+rhadGti12v7IiLBYY+Sb41YGD6+DXB8AwCtci2nPsBEf/0QIlIiJSVRSI5KzaNwxh7IDmADzx83qS0rJ49heztehfvZsQW6/4/cpOE1QfLv0QLFZY/QUseodgX2+aRwQAsFbdZiIi4iblCkSffvop06ZNK/z9oYceIjQ0lD59+rB7dzl3SxePdveQWFrUC+RIeg4Xv7OQ7YczqBtg596hLcp2ohZDYdh48/7MJ2DL74UDq7XzvYiIuEu5AtELL7yAn585vXrRokXEx8fz8ssvEx4ezv333+/SAsUz+HjZeOWKOKwW2J9irkv072GtCPHzLvvJet4OXW8EDPjhZgaFHga0QKOIiLhPuQLRnj17iI2NBeCnn37isssu47bbbmP8+PH89ddfLi1QPEenmFBuzZ9a36FhCFd0iynfiSwWuOAVaHoO5KQzbO191CWFNXuTS71ViIiIiCuVKxAFBgZy9OhRAGbOnMm5554LgK+vLydOlG1DUE8UHx9P27Zt6d69u7tL8Tj/HtaKN67qxEeju2GznmUgdUls3nDFpxDWDHv6Xt63/4/MzEwSj2W6rlgREZFSshjl+F/y6667js2bN9O5c2e++uorEhMTqVu3LlOnTuWxxx5j/fr1lVFrlUtNTSUkJISUlBSCg4PdXU7NdGQbfDAEslP4wdEfr0sncFHnaHdXJSIi1Vh5/n6Xq4UoPj6e3r17c/jwYX744Qfq1q0LwIoVK7jmmmvKc0qprcJbwJWTcGLjMttfBCx/x90ViYhILVSuFqLaQi1EVWfNlFeJW/scTixYr/oC2lzo7pJERKSaqrIWot9//50FCxYU/h4fH0+nTp249tprOX5cKw5L2QWfM5ZP887FioEx5TY4sNbdJYmISC1SrkD073//m9TUVADWrVvH//3f/3HBBRewc+dOHnjgAZcWKLVDk7r+vOl1M3852mPJzYCvroG0Q+4uS0REaolyBaKdO3fStm1bAH744QcuvPBCXnjhBeLj45k+fbpLC5TawWKx0L5RXcbl3kNKQBNI3QtfXwu51X/WooiIeL5yBSK73U5mpjk9etasWZx33nkAhIWFFbYciZRVp+gQUgnkvaj/gm8o7FsOP98FGuYmIiKVrFyBqF+/fjzwwAM899xzLF26lBEjRgCwdetWoqM1ZVrKp2ALj1lJQXDV52D1gvXfw/xX3VuYiIjUeOUKRO+88w5eXl58//33vPfeezRs2BCA6dOnM3z4cJcWKLVHQSDafjid1Kje5mrWAHOehw0/ua0uERGp+TTtvgSadl/1+r30J3uPn+DLW3rSJzYcpj8CS94DLz+4aTo06OzuEkVExMOV5++3V3kv5nA4+Omnn9i0aRMA7dq1Y9SoUdhstvKeUoS4mFD2Hj/B6r3JZiA673k4ug0SZpkzz26dA8FR7i5TRERqmHJ1mSUkJNCmTRv+9a9/MWXKFKZMmcL1119Pu3bt2L59u6trlFqkU3QoAKsTk80HbF5w+ccQ3grSDsDX10CO9jsTERHXKlcguueee2jevDl79uxh5cqVrFy5ksTERJo2bco999zj6hqlFunUKBSANXuTTz7oGwLXfg1+YbB/FUy5FRx5bqlPRERqpnIFonnz5vHyyy8TFhZW+FjdunV58cUXmTdvnsuKk9qnXYNgbFYLh1KzOZiSdfKJsGZw1Rdgs8PmX+GnseB0uK9QERGpUcoViHx8fEhLSzvt8fT0dOx2e4WLktrL3+5Fy/pBAKze849tYJr0hSs+Nafjr/sWfr1PaxSJiIhLlCsQXXjhhdx2220sWbIEwzAwDIPFixdzxx13MGrUKFfXKLVMp5gQAFbvSTn9ydYXwKXvg8UKKz+D3x9RKBIRkQorVyB66623aN68Ob1798bX1xdfX1/69OlDbGwsb7zxhotLlNqmU/56RGv2JBd/QPvL4KJ48/6SCTDraYUiERGpkHJNuw8NDeXnn38mISGhcNp9mzZtiI2NdWlxUjsVLNC4bl8KDqeBzWo5/aBO+fucTXsAFr4B9gAY8FCV1ikiIjVHqQPR2XaxnzNnTuH9119/vfwVeYD4+Hji4+NxODRo1x1a1AvC324jPTuP7YfTC8cUnab7zWYomvk4zPkvePtBn7urttgqMnXNfoJ8vBjUup67SxERqZFKHYhWrVpVquMslmL+b76aGTduHOPGjStc6VKqls1qoX3DEJbuPMbqPclnDkQAfe4yQ9Gc52Hmf8DLF3rcWnXFVoE9xzK556tVeNssrHjiXIJ9vd1dkohIjVPqQHRqC5BIZescE8rSncdYsyeZK7vFlHzwOQ9CbiYseB1+exC8/aHzdVVTaBVYtusYALkOg4XbjnB+B63ULSLiauUaVC1S2QrGEa0+08DqU1ksMORJ6DnW/H3qXbDu+0qrraot331y+YE5W5LcWImISM2lQCQeqSAQbT6YRlZuKcZyWSwwfDx0HQOGE6bcBpt+rdQaq8rKUwLRvK2H0X7MIiKup0AkHqlBiC/hgT44nAYb9hezHlFxLBYY8T/oeDUYDvj+Rtg2q3ILrWSpWblsOWQugmr3snIoNZtNB05fFFVERCpGgUg8ksViKVyPqNgFGs/EajXXKGp7EThy4JvrYOdflVNkFViVmIxhQKMwf/rHhgMwd6u6zUREXE2BSDzWyRWrk8v2QpsXXPohtBwOeVnw5VWwZ6nrC6wCK/K7y7o1rsPAVhEAzN1y2J0liYjUSApE4rHizrZidUm87Oa+Z80GQm4GfHEZ7C/d0hGepGD8UJfGdRjYylyDaMXu46ScyHVnWSIiNY4CkXisjtGhACQey+RYRk7ZT+DtC1d/CY36QHYqfH4JHNro2iIrUZ7DyarE/BaiJnWICfOneUQADqfBwoQjbq5ORKRmUSASjxXi502ziAAA1uxNLt9J7AFw7TfQsCucOA6fjYJF70LGUdcVWkm2HEojI8dBkI8XLeqZi1MWtBLN1fR7ERGXUiASj9Ypv5VodWJy+U/iGwzX/wCRHSDjMMx4FF5rBd+OhoRZ4PTMLVoKxg91ahRauJ9bwTgiTb8XEXEtBSLxaIXjiMrbQlTArw7cNANGvAZRncCZCxt/MscWvdER5rwAx3dXsFrXOjmgOqzwsR5Nw/Dztmn6vYiIiykQiUfrdMrA6gq3iNgDoPstcPs8uP0v6HEb+IZC6l6Y9xK8GQefXWSucp2bVeHaK6ogEHVtXKfwMR8vG32a1wU0/V5ExJUUiMSjtY4Kwm6zcjwzl8Rjma47cVRHuOAV+L8tcNlH0HQAYMCOufDDzfB6a/jtITi4znXXLINDqVnsPX4Cq8XsMjvVwPwd7+du1vR7ERFXUSASj+bjZaNNg2CgHOsRlYa3L3S4HEZPhXvXwDkPQXBDcwD20okwoR+8PxCWfQRZZVggsoIKWodaRwYT6FN0D+aBLc1xRCsSNf1eRMRVFIjE43WKNhdoXFOWFavLo04TGPw43LcOrvvBXO3a6m2uXzTtAXi1Ffz5X6iCwczFdZcV0PR7ERHXUyASj1fQZVThgdWlZbVBi6Fw5Wfwf5th2AsQ0QbyTsD8l+Hvtyq9hOUlBCLQ9HsREVdTIBKPF5c/9X79vhRyHc6qvXhAOPQeB3cugvOeNx/740nY8FOlXTIr18GGfWZr2JkD0cltPDT9XkSk4hSIxOM1qRtAsK8X2XlOthx001RziwV632XOTAP48XbYs6xSLrV2bwp5ToN6QT5E1/Er9piC6fdJadlsPJBaKXWIiNQmCkTi8axWS+F6RJUysLq0LBYY/uLJTWO/uhqO7XT5ZZbvPgaY23VYLJZij/HxstE3Nn/6vTZ7FRGpMAUiqRY6eUIgAnN80WUfQWRHyDwCk6+AzGMuvUThhq6Niu8uKzAgfxzRPAUiEZEKUyCSaqFgHNEadwciAJ9AuPZbCI6Go9vgmxsgL9slpzYMo8QZZqfS9HsREddRIJJqoWOMOfU+4XA6aVlV/8d/x+F0Lnl3IS/8tsl8IDgKrvsW7EGwewFMvccl0/F3HMngeGYuPl5W2jUIKfFYTb8XEXEdBSKpFuoF+dIw1A/DgHX7qm6BRDBnt10xYRGrEpP58K8dHE7Lbw2q3w6u/BQsNlj7Ncx9scLXKmgdiosOxe519n89C6bfz9ms6fciIhWhQCTVhjvGES3afpSr31/M0YwcAJwGTF9/4OQBsUPgwv+Z9+e9CKu/rND1VuzKHz90lu6yAoMKxhFt1fR7EZGKUCCSaiMuv9ts9qYkMnPyKv16MzYcZPQnS0nPzqNn0zDuHdICgF/XHCh6YNfR0O9+8/7Ue2Dn/HJfc0ViwQ73pQtE3ZvWwd+u6fciIhWlQCTVxsBW9bBZLazYfZyRby9g4/7KCwDfLt/D2C9WkJPn5Ny29fn0ph5c3SMGgKW7jnEg5UTRFwx+EtpdCs5c+Pp6OLylzNdMzswhISkdKH0LkY+XjT7NNf1eRKSiFIiKER8fT9u2benevbu7S5FTtKwfxOc39aB+sA/bD2dwcfxCJi3c6fKuoonztvPQ92txGnBF12jeu64Lvt42okL86N7EDCrT1v6jlchqhYvfg5iekJ0Cky+H9LKN61mZ3zrULCKAsAB7qV+n6fciIhWnQFSMcePGsXHjRpYtq5yViKX8+sSGM/3ecxjaph45DidP/7KRWz9bzrH8MT4VYRgG46dvYvz0zQDcfk4zXr68I162k/+ajIxrAMCv/wxEAN6+cPVXUKcpJCeaCzfmZJb6+oXT7c+y/tA/afq9iEjFKRBJtRMWYOeDf3XjmVHtsHtZmbUpifPfnM/f28s/9TzP4eSRH9Yxcd4OAB45vzWPXtDmtJWiz28fhdViDuzec6yYsBNQF677HvzqwL4V8ONt4Czd/mulXX/on2LC/ImtF4jDabBgm6bfi4iUhwKRVEsWi4XRfZrw0519aR4RwKHUbK77cAmvzNhc5g1gs3IdjPtyJd8s34PVAi9d1oE7BjQv9tiIIB96NTPH7BTbSgQQHmu2FNnssOkX+OOJs9aQ63AWzp7r1qRsgQhOthLN3aLp9yIi5aFAJNVa2wbB/HJ3P67uHoNhQPyc7Vw5cVHxrTfFSMvK5cZPljFjwyHsNivvXteVq7o3KvE1Bd1mv6zZf+aDGvc2xxQBLHoHln1Y4jk3HUglK9dJiJ83zcIDS1X7qQZq+r2ISIUoEEm152/34sXLOhJ/bReCfL1YlZjMBW/+VXJgAY6kZ3PNB4tZtOMogT5eTLqpO8PbR571esPbReJltbDxQCo7Dqef+cAOl8Pg/5j3f/s3bJ15xkOXF6w/1CgUq7X4DV1Loun3IiIVo0AkNcaIjlFMv7c/XRvXIS07j7u/WsXD368tds2ivcczuXLCItbvSyUswM5Xt/aiT/PwUl2nToCdfi3MY8/YbVag/4PQ+XownPDdGPj9Mdj2B+RkFDmscP2hJmGlquGfNP1eRKRiFIikRomu4883t/XinsGxWCzwzfI9XPj2AjbsP7ndx7ZDaVz+3iJ2HMmgYagf39/Rmw7RJe8b9k8XdixFtxmAxQIXvgHNBkJuBiyON6fkv9gYPhkB816BPctYs8scDH22He5LUtBtpnFEIiJlZzE04OCMUlNTCQkJISUlheDgYHeXI2W0aPtR7v9mNQdTs7DbrDx6QWviYkK5adIykjNzaVEvkM9u7kFUiF+Zz52alUu352aR43Ay475zaBUZVPIL8nJg86+wYw5snwspiUXPZ/iz2GjLwOFXYG85FOo2N8NUGew9nkm/l+Zgs1pY+cS5hPh5l/FdiYjUDOX5+61AVAIFourveEYOD/2wlj82HgLMjGEY5r5on4zpTp0yLID4T7d+tpw/Nh7irkGxPDisVelfaBhwbAfsmAs75pKTMBd77j/G/QRHQ/OB0GwQNB0AgRGlOvXQ1+eRkJRO/LVdGNExqvQ1iYjUIOX5+60uM6nR6gTYef+Grjx3kblmkWFA/xbhTL6lZ4XCEMCF+YHj17X7yzazy2IxW4C63wxXfc749tMYlf0csxrcAU36m9P1U/fCqi/gh5vh1Vh4rx/MexlOJJd4ak2/FxEpHy93FyBS2SwWCzf0bkLv5uGs3pPMqLgG2L0q/v8CQ9vUx9fbyq6jmWzYn0r7hmUbh1RgWWIK643mZPW6HDo2MFe3Tvy7sAWJg+vgUP5t0TvQ+27odQf4nN5NN7BVPT5csJO5+dPv/7mwpIiIFE8tRFJrxNYL5PKu0S4JQwABPl4MaV0fKMXg6jPIyM5j04E04JQVqu3+EDsUznse7lgADybAxRMgojVkpcCc5+GNjrDgjdNmqxVMvz+cls2GStz8VkSkplEgEqmAk91mB8q1IOKavck4nAYNQnzPPLg7MAI6XQNj/4bLPoK6sXDiGMx6Ct6Mg0XxkHsCKJh+by4JMG+rpt+LiJSWApFIBQxqXY8Au419ySdYmZhc5tevyF+QsWtp1h+y2szFHu9cYq6CXacJZByGGY/BW51h6QeQl83AVhpHJCJSVgpEIhXg623j3LZmt9mva8vebVawIGPXRqGlf5HNCzpdC3cth5FvmjPS0g7Abw/CW10YkfM7XuSxMjGZlBO5Za5JRKQ2UiASqaCCvc2mrT2Aw1n6bjOn02Bl4Q735Vih2uYNXcfAPSvhglchKApS91Lnz4f4y+/fXGKZy8ItB8t+XhGRWkiBSKSC+reIINjXi6S0bJbtOlbq1yUcTic1Kw8/bxttos6ysGNJvHygx61wz2oY/iIE1CPKOMSr3hPp/ttwWPstOB3lP7+ISC2gQCRSQXYvK8PamZvClqXbbEV+61CnmFC8bC74V9HbF3qNhXtXs6vzwxwzAonI2QtTboV3e8PyTyC7hM1oRURqMQUiERco6Dabvu4geQ5nqV5TsMN94XR7V7EHEDXiYc4z3uGV3Ctx2IPhyBb49T54rRX8ch8cWOPaa/6DYRhsPpjKh3/t4N6vV7Fo+9FKvZ6ISEVpYUYRF+jTvC5hAXaOZuSwaMdR+rc4+1YbKwsGVDdxcSDCnH7fqXkM8ZsuJrT7ndzq/xesmATHtsOKT8xbw67mGKT2l4E9oMLXTErNYkHCEf7adoQFCUc4nJZd+Nxv6w7w2pWdGJUfHEVEPI0CkYgLeNmsnN8+kslLEvllzf6zBqKj6dnsPGIuqtglxvWBCGBgqwhmbTrEzO0nuPWOe6DP3bBzvhmGNv0K+1aYtxmPQ8croeuNENm+1OfPzMljyc5jLNh2hAXbjrDlUFqR5329rfRsWhcw10S656tVHE7L5uZ+TV36PkVEXEGBSMRFLuzYgMlLEvl9/UGev7hDiStiF4wfalk/kBD/ytmVvmA9ohW7j5OSmWtep9kA85Z+GFZPNluNju+EZR+at+juZjBqd4m5YvYpHE6D9ftS8luBDrNydzI5p3QPWizQvkEI/VuE069FOF0b18HHy4bTafDsrxuZ9Pcunvt1I0mpWTw8vDVWq7YVERHPoUAk4iI9moYREeTD4bRsFiQcZnD+th7FKVx/yNXjh04RXcefFvUC2ZaUzl8Jh7mw4yndVYER0O8+6HMP7JxnthptngZ7l5m3GY/i6HA12xtdwZL0CBbtOMrf24+SnFl0XaOGoX6FAahv8/BiN8y1Wi08NbIt9YN9een3zUycv4PDadm8dHlHvF0xmFxExAUUiERcxGa1MKJDFJP+3sUvaw6UGIgK1h/q0qjyAhGYrUTbktKZu+UfgaiA1QrNB2E0G8jexF2kLZlEVMI31Mk6gG3ZRFoum0iysxWL84aR7OxJkI83vZvXzQ9BETSp61+qDWQtFgtjBzYnIsiHh39Yy5RV+ziSkcN713UhwEf/GRIR99N/iURcaGScGYj+2HiIrFwHvt62047JznOwZm8KAN1Ks2VHBQxsVY8P/trJvK2HcTqNwm6qo+nZrNmbzOo9KazZk8yavcn5rT89sNCN/tZ1XGv7k6G2FfSwbqGHfQvjo/rgf/EbeNVvVe56Lu8aTd1AO3d+sZL5Ww9zzQeL+XhMd8IDfVz0jkVEykeBSMSFOsfUoWGoH/uSTzB3SxLD20eddsyG/ank5DkJC7DTpK5/MWdxnW5N6uBvt3E4LZuXZ2xh7/FM1uxNZs+xE6cda7dZadsgmE4xoXSK6UKrmHux2VPMcUYL3yL4wN/wfj/o9wD0u99c96gcBrWqx1e39eKmSctYuzeFy9/7m89u6kmjSv4sRERKokAk4kJWq4URHaN4f/4Ofll7oNhAVLCha5dGdUrV3VQRPl42+jQPZ9amQ0yYt73Ic80jAoiLCc0PQKG0jgwuZiB4AAx6zNw7bdqDkPAHzHsR1n0HF74OzQaWq65OMaF8f0dv/vXxUnYdzeTS9/5m0o3dad8wpHxvVESkghSIRFxsZMcGvD9/B39uSiIzJw9/e9F/zQpmmHWrhPWHinP7gGbsTz5Bg1A/OjcKJS46lA7RIYT4lWF2W50mcN13sPEnmP6IuZ7RZxdBhyth2H8hsF6Z62oWEciUsX0Y/ckyNh1I5er3FzPh+q70axFe5nOJiFSUpniIuFj7hsE0ruvPiVwHszYlFXnOMIwqmWF2qu5Nwvjt3v58OLob4wbF0q9FeNnCUAGLxZyOf9dS6HEbYIF138I73cxtQZylW6H7VPWCffnm9l70blaX9Ow8bpy0lKlrSr/9SWV6e/Y2rpy4iGMZOe4uRUSqgAKRiItZLBYu7Gh2lf36jz/ue46d4HBaNt42Cx2qa/eQbwhc8ArcOhsiO0JWirktyMfD4NCGMp8u2NebSTd1Z0THKHIdBvd8tYqPFux0fd1l8Pni3bz2x1aW7jzGN8v2uLUWEakaCkQilaBgb7O5Ww6TmnVy7Z4ViccAaN8wpNgZaNVKw65w6xwYNh7sgbB3KUzoDzOfgJyMMp3Kx8vG21d3ZkyfJgA89+tGxk/fhNNpVELhJftr22Gennoy2P2wci+GUfV1iEjVUiASqQSt6gcRWy+QHIeTPzYcKny8YPxQ10pef6jK2Lyg950wbim0GQmGA/5+C+J7wZbfy3SqggUcHx7eGoCJ83bw4HdryC3lZrmukJCUzp2TV+JwGozoEIWPl5WEpHTW7UupshpExD0UiEQqgcViYWT+Qoi/rj3ZbVaww31VDaiuMiEN4aov4JpvICQGUhLhq6vgm+shZV+pT1OwgOOrV8Rhs1qYsmofN3+6nIzsvEos3nQ8I4dbPl1GWlYeXRvX4fWr4hjWLhKAH1bsrfTri4h7KRCJVJIL48xxRH9tO8LxjBzSsnILN0Ct7BWq3abVcBi3xNxI1mKDTb9AfA9Y+XmZTnN512g+HN0NP28b87ce5vqPlpCcWXmDm3PynIydvIJdRzOJruPHxBu64uNl49IuDQGYumY/OXlV11IlIlVPgUikkjSPCKRNVDB5ToMZGw6yek8yhgExYX7UCy7foobVgj0Aznsebp9nbhabkw5T74Kf7oSczFKfZlCrenx5a09C/b1ZlZjMlRMXcTAly+XlGobBkz+vZ/GOYwT6ePHR6JMrZ/eLDadekA/HM3OZsyXpLGcSkepMgUikEo3MbyX6Ze3+k91ljSt3uw6PEdkBbpoJQ54EixVWT4YPh8KRhFKfonOjOnx7e2/qB/uw9VA6l0/4m51HyjZg+2w+WrCTr5ftwWqBt6/pTKvIoMLnvGxWLu5sthJNWaluM5GaTIFIpBJd2MEcR7Ro+1H+2GgOru5SResPeQSrFfr/H/zrZwiIgKQN8P5A2PBTqU/Rsn4Q39/Rh6bhAew9foIrJvzNehcNcp696RD//W0TAI+PaMug1qcvMHlZl2gA/tycxHGtSSRSYykQiVSiRnX9iYsJxWnAxgOpQA2aYVYWTc+B2/+CRn0gJw2+Gw2/Pwp5pQsYMWH+fHt7b9o1COZIeg7XvL+YJTuOVqikTQdSueerVRgGXNOjETf1bVLsca0ig2jXIJhch8Evaz1j0UgRcT0FIpFKNrLjyf3MAn28inTJ1CrBUTD6F+h7r/n74ndh0ohSz0KLCPLhq9t60aNpGGnZefzr46XM2njo7C8sxuG0bG75dDkZOQ56N6vLsxe1K3FfuYJWoh9Wln7GnIhULwpEIpXsgg4nA1HnRqHYrJW7oatHs3nBuc/C1V+CT4i5mOPE/pAwu1QvD/b15rObejC0TX2y85zc/sWKMk+Jz8p1cPvny9mXfIKm4QG8d30XvG0l/6dwVKcGeFktrNmTTEJSepmuJyLVQ40PRHv27GHgwIG0bduWjh078t1337m7JKllGoT60T1/3aGq2r/M47UeYc5Ci+wImUfhi8tg7ovgdJz1pb7eNiZc34XLukTjcBr833drSr3Vh2EYPPzDWlYmJhPs68VHo7sR6m8/6+vCA30Y2CoC0OBqkZqqxgciLy8v3njjDTZu3MjMmTO57777yMhw7SwVkbN5ZlR7ru3ZqHBrCgHCmsLNf0DXMYABc8fD5Msh4+xjg7xsVl65vCM392sKmFt9vDpjy1m32Iifk8DPq/djs1p47/quNIsILHW5l+Z3m/24ah8ON2wpIiKVq8YHoqioKDp16gRAZGQk4eHhHDt2zL1FSa3TtkEwL1zSoVStEbWKty+MfBMungBefrD9T7MLbc/Ss77UarXwnxFt+PewVgC8MyeB//y0/oxh5bd1B3h15lYAnr2oHX1jw8tU6pA29Qj29eJAShaLKzigW0Q8j9sD0fz58xk5ciQNGjTAYrHw008/nXZMfHw8TZo0wdfXl549e7J06dn/Y1mcFStW4HA4iImJqWDVIuJSna6BW/+EurGQug8+OR8WvwdnafGxWCyMGxTLC5d0wGKByUsSuefrVaetKr12bzIPfLsagBv7NuG6no3LXKKPl61w015t5SFS83i5u4CMjAzi4uK46aabuPTSS097/ptvvuGBBx5gwoQJ9OzZkzfeeINhw4axZcsW6tUz1wzp1KkTeXmn73U0c+ZMGjQw/wN27Ngx/vWvf/HBBx9U7hsSkfKp3xZumwtT74YNP8Lvj0DiIhj1DvgGg9MJeVmQewJyM82feScg9wTXhmfScsBxJi/YhNeGHL5653uu6RyO3cghLdfKzMUHGem00SS6Hne09IJdyWD3B3ugubK2t7/50+ZdYomXdolm8pJEpq8/yHMX5xHg4/b/hIqIi1iMs3W6VyGLxcKPP/7IxRdfXPhYz5496d69O++88w4ATqeTmJgY7r77bh555JFSnTc7O5tzzz2XW2+9lRtuuKHE47Kzswt/T01NJSYmhpSUFIKDg8v3pkSkbAwDln4AMx4DZ67ZlYZhhqHKZrObwcgeaIak4CjofAO0vQhs3hiGweDX5rHzSAavXhHH5V2jK78mESmz1NRUQkJCyvT326P/9yYnJ4cVK1bw6KOPFj5mtVoZOnQoixYtKtU5DMNgzJgxDB48uMQwBDB+/HieeeaZCtUsIhVksUDP26BhF/huDKTsOf0YL1/z5u0P3n6n/PQlJc+bxXsySc3zJtdqx+bMo453Dv0b++FnZJt7q+VkmK1MBfed+S3Mjhw4kQMnzG1WOLIFdsyFmU9Aj1uwdL2RSzs35LU/tjJl5V4FIpEaxKMD0ZEjR3A4HNSvX7/I4/Xr12fz5s2lOsfChQv55ptv6NixY+H4pM8//5wOHTqcduyjjz7KAw88UPh7QQuRiLhBdDe4eyUk7wYvn5Ohx8vP3BLkDEKAZofSuOGjpRxMzcJuszJ5dE/8mpSwh1xezulBKTvd7LJb9iGk7YfZz8K8l7mx9WVMtcSxaAfsSz5Bw1A/1793EalyHh2IXKFfv344nc6zHwj4+Pjg4+NTyRWJSKl52SG8RZlf1qJ+EN+P7c1bs7dxfvsoupcUhgqu4xUG/v84rtkA6Hc/rJ9irqx9cC2B6yfzh89k/nK0Z9WsQzS8dEyJAU1EqgePDkTh4eHYbDYOHSq6PP+hQ4eIjIx0U1UiUh1E1/Hn5cvjKn4iLx9zFlzc1WaL0eJ3MTZNo79tPay/H2P/O1h63g6drgWfWroti0gN4NH/W2O32+natSuzZ59c1t/pdDJ79mx69+7txspEpNaxWKBxH7jqCzLHruAj50hSDX8sx7bD9Ifg9bbw+2NwfJe7KxWRcnB7IEpPT2f16tWsXr0agJ07d7J69WoSExMBeOCBB/jggw/49NNP2bRpE2PHjiUjI4Mbb7zRjVWLSG0WUL8Z69s9SK/sd/gl+v+gbgvIToXF8fBWZ/j6Oti14KzrKImI53D7tPu5c+cyaNCg0x4fPXo0kyZNAuCdd97hlVde4eDBg3Tq1Im33nqLnj17Vnpt5Zm2JyK1w1/bDnPDR0sJ8fNm6WOD8Nk111xMcvspG9XWawc9boEOV4JP6bcJEZGKKc/fb7cHIk8UHx9PfHw8DoeDrVu3KhCJyGkcToO+L/7JwdQsJlzfheHto8wnDm+BJRNg9VfmwpEAPsHmGKPut5RrkLiIlI0CkYuphUhESvLi9M1MmLedoW3q8+HobkWfPHEcVk2G5R/BsR0nH282ELrfCi2Hg82j57WIVFvl+fvt9jFEIiLV1WVdGgIwd0sSR9Oziz7pVwf63AV3rYDrf4CW5wMWc6HHb66DN+Ng/quQfrjK6xaR0ykQiYiUU4v6QXSMDiHPafDLmv3FH2S1QuxQuPZruHcN9L0P/MIgdS/8+Ry83gZ+uAUSl2gQtogbKRCJiFTApZ3NVqIfVu47+8F1GsO5z8ADm+DiCdCwm7lf27rv4OPzYGJ/WPEp5GRWctUi8k8KRCIiFTCqU0O8rBbW7Uth66G00r3I29dc7PHW2XDbXOh0vbk328F18Ms98Hpr+P1ROLi+UmsXkZMUiEREKiAswM6g1vUA+GHl3rKfoEFnuDjebDU69zmo0wSyUsytQib0hff6wsK3IPWAawsXkSIUiEREKuiyLuau9z+t2ofDWc5xQP5h0PceuHsVXPsdtBkJNjscWg9/PAH/awufXwJrvjE3oRURl9Kcz2Kcug6RiMjZDGodQai/N4dSs1mYcIRzWkaU/2RWK7Q8z7xlHoMNP8Lab2DPEtj+p3n7NQDajoKOV0HTc8Bqc92bEamltA5RCbQOkYiU1pM/r+ezRbu5uFMD3ri6s+svcGwHrP0W1nwNx3eefDwoCjpcYW4+W79d+c7tyIOMw5B+ENKTwJELsUPA2881tYtUMS3M6GIKRCJSWqv3JHNx/EJ8va0se3woQb7elXMhw4A9S2Ht17B+CmQln3wusgN0vNoMSEH1zdlq6YfMW9rBU+4fMsNPWv7vGYeBf/wpqNsCLoqHRpW/TZKIqykQuZgCkYiUlmEYDH19HtsPZ/Dy5R25sltM5V80Lxu2zjC71LbOMKfwA1isYA80N5wtLYsVAuqZQSp1f35IskCvsTD4CbD7V8pbOI1hgMVSNdeSGkuByMUUiESkLOLnJPDKjC30ahbG17f1rtqLZx6DDVPMLrW9y04+7uVnhpzAyPyf+begyKL3/eueHIt04jjMeBxWTzZ/r9PUbC1q0rfy6j+yDea+CJt/hYGPQr/7Ku9aUuMpELmYApGIlMX+5BP0felPDAP+emgQMWFV1KryT8l7IC/LDDs+QeVvcdn2B/xyL6TmLzrZ4zYY8hT4BLqu1mM7YN7LZiuX4Tz5+Mg3oesY111HahXtZSYi4kYNQv3o07wuYE7Bd5vQGAhvAb7BFet+anEu3LkIuow2f1/6PrzX29yPraKSE+Hnu+DtbrDmKzMMtRoB3W8xn//1ftj0S8WvI5Xq4wU76frcH6zfl+LuUipMgUhExIUu7WyuSTRl1T5qRAO8bwiMegtu+BFCYswg89lF8Mt9kFWGMUoFUvaZYeetLrDqczAcEHsu3DoHrvkSLnjVDGCGE76/GXYtdPlbEtc4mp7NKzO2cDQjh+9XlGNRUg+jQCQi4kLD20fib7ex80gGKxOTq/z6J3Ic3Dl5Bfd9vYptpd1KpDSaDzZbi7rdbP6+4hN4tzckzCrd69MOwvSH4a3OsPxjcwB4s4Fw8x9w/ffQsIt5nMUCI16H1heCIxu+ukZbmHio9+fv4ESuuV7fwoQjbq6m4hSIihEfH0/btm3p3r27u0sRkWomwMeL4e0jAdzyf80f/LWD39Yd5KfV+znvjfnc9/Uqdh5x0crWPkFw4esw+hdzi5HUvfDFZfDzODiRXPxrMo6YA7Tf7ARLJpghp3FfGDMN/vUzxPQ4/TU2L7jsQ2jUB7JT4ItL4fgu17wHcYkj6dl8tmh34e/bktI5lJrlxooqToOqS6BB1SJSHn9vP8K1HyzB7mVl1v0DaFS3agZXJ6VmMfDVuWTmOOjcKJRV+S1UNquFSzs35J4hLVw30DsnA2Y/C0smAoa5QOTIN6HlMPP5zGPw91uw5H3IzQ9k0T1g8OPQdEDpxjadSIZJI8ztS8KawU0zIbACq4CLy4z/bRMT5+8gLjoEh2Gwfl8qr18Zx6X529i4mwZVi4h4gN7N6tKneV1y8py88NumKrvu639sJTPHQaeYUKaM7cOvd/djcOt6OJwG363Yy6BX5/LYj+vYn3yi4hezB8D5L8GN0yGsOaQdgC+vhCm3w5wX4I2OsOB/Zhhq0Bmu+x5unml2k5V2oLdfqPm60EbmbLTJl0O2C7sB/0ntA6VyauvQfUNb0i/WDKkLE466s6wKUyASEXExi8XCUyPbYbNa+H3DQf6ugvEVmw+m8u3yPQA8cWEbLBYL7RuG8PGY7ky5sw/9W4ST5zT4ckkiA1+Zy9NTN5Dkii6Oxr3hjgXQ+y5zcce1X8O8lyAnDep3gKu/MgdMtzi3fDPegqPg+h/NdZIOrIZvrjcXpHSl7DT440l4sbEZ5qREBWOH4mJCGdgqgr6x5szKhQlHqvVEAgUiEZFK0CoyiOt7NgLgmV82kudwnuUVFfPfaZtwGnBBh0i6Ng4r8lyXRnX4/OaefHt7b3o2DSPH4WTS37s455U5/HfaRo6mVzBg2P1h2H/NLq3IDubtik/h9vnQ+oKKrzwdHmu2FNkDzSn/P94BThd8nk4nrP4K3u4KC980xyvNewmWf1Lxc9dQZuvQLgDuG9oCi8VC9yZh2L2sHEzNYoerxqu5gQKRiEgluf/cltTx92bLoTQmL0mstOvM23qYv7Ydwdtm4eHhrc94XI+mYXx9Wy8m39KTLo1Cycp18sFfO+n/8hxembGZ5MycihUS091sLbpjAbS7GKwu/BPTsAtc9TlYvc0VuX9/uGJdXPtWwMfnwU93mPu5hTWDTteZz037P9g+xzV11zDvz99BVq7TbB1qaXaV+Xrb6NqoDlC9Z5spEImIVJJQfzsPnNcKMMf3HM+oYOAohsNp8MI0c5zS6N5NaFw3oMTjLRYLfWPD+WFsHz65sTsdGoaQmeMgfs52+r80hzdmbSU1K9fldbpE88FwyQTAYi4S+derZT9HepI5K+6DweYWJ/ZAGPo03LnY3J6k41Xm2kjfjobDW1z9DoqXewKWfVh11yunw2mntw4V6NciHKjegcjL3QWIiNRk1/ZoxOTFu9l8MI3X/tjC8xd3cOn5v12+hy2H0gjx8+buwS1K/TqLxcKgVvUY2DKCPzYe4vU/trL5YBpvzNrGh3/tpHFdf8IC7IQH+hAWYKduoJ26AXbqBvgQVnA/0IcAu63IH8ZK1+FyyDwK0x+CP5+HgIjSbfGRlwNLJ5rbhBRsetvxajMMBUedPG7U2+bik4mLYPIVcOufEBBeGe/ElJ0OX10Nu/4CvzC44y8I8YyZWv/0/vztZOU66XRK61CBvrHhvDJjC39vP4rDaWCzVr8NehWIREQqkc1q4elR7bj6/cV8uSSRa3s0pm0D1yzjkZ6dx2sztwJwz5AWhPh7l/kcFouF89pFMrRNfX5bf4D//bGV7Ycz2LC/dKtQ272shAfY80OSD3UD7AxqXY+RcQ3KXEup9bzdbOn561Vz1Wv/utBm5JmP3zYLfn8Ejm4zf4/qBBe8UvwaSF4+cNVk+HCwufbR19fB6Knm4652ItkMXXuX5v9+DL67EW78DWxl/2dZmQ6nZfP54oKZZS1OC8EdGoYQ5OtFWlYe6/al0Ckm1A1VVowCkYhIJevVrC4jOkQxbd0Bnv11A1/d2sslrSoT523nSHo2Ter6c0OvxhU6l9Vq4cKODTi/fRSbDqRyOC2boxk5HE3P5lhGTpH7R9JzOJqRTVauk5w8J/tTstifcnLG2pRV+3AaBhd1aljRt3hmg/8DGUmw8jNzi48bppAW2ZNch0FYgN085uh2c1HIrdPN3/3DzRahTteVPL4poC5c+x18OBT2LDb3XLv0/YoPDj9VxhH4/BI4uBZ8Q+HC/5nboexdCn88BcM9a7bbxHknW4cGtDx9LSib1ULvZnWZufEQCxOOKBCJiEjxHr2gNbM2HWLxjmNMX3+QCzpEnf1FJTiQcoIP/toBwCPnt8bu5ZohoTarOV2/NDJz8jiaboalYxnZHEnPYfH2o0xZtY+Hf1hLbL1A2jUo3bnKzGKBEf8zF4Dc/CvOL6/mTuNp1uTG8Me4btRf8zYsigdHDli9oMftMOAhc22j0ohoCVd9Zq7Eve5bqBsLAx92Te2pB+Dzi+HwZrPL74afILK92Qr19bWwOB4a9YS2F7nmehWUlJbFF0vO3DpUoG9seGEgGjcotipLdAkNqi6Gtu4QEVeLruPP7QOaA+YU+az8PaDK65UZW8jKddKjSRjD2kW6osQy87d7ERPmT6eYUAa3rs+V3WJ45Yo4BraKICvXyW2freBYJQwkL5S/xUdedC+sOWm8lvMcl+ROw29id3NRSEeOORB77N9mi0tpw1CBZgNhxGvm/bkvwLrvK15zciJ8cr4ZhoIbwo2/m2EIoPUI6HO3ef/nu8wWLg/w/jxzZlnnRsW3DhXoG2uOtVq++3iFv9/uoEBUjHHjxrFx40aWLVvm7lJEpAYZO6A5DUJ82Zd8gonzdpT7POv3pTBl5T4AHh/RpmoHNZ+FzWrhzas607iuP/uST3DXlysrdQ2mXKsPd/Ewm5wx1LMk84z3pwTnHSUvuLG5KOT1UyCiVfkv0HXMyZDy052QuKT85zqSAB+fD8d3mnvB3TjdXGPpVEOegka9zYHf3/7LnIHmRkVbh1qW+F1rHhFAZLAvOXlOlu86XlUluowCkYhIFfGz23j0gjYAvDcvgX3l2ELDMAyen7YRgIs6NSDOA8dqhPh78/4N3fC32/h7+1FenL65Uq5jGAZP/ryB3xNOcLvxGNnBTcmy+PBy7lU8Gf2haxaFBBj6DLQaYW5M+/W15dto9tAGs2UodS+EtzTDUJ1ixn3ZvOHyj83xTofWw2//rnD5FTHxlNahc1qUPNvOYrHQp2DV6u3Vb/q9ApGISBW6sGMUPZqGkZXrZHw59jmbvSmJxTuOYfey8u9hFWj5qGStIoN47Yo4AD5csJOfV+9z+TXen7+Dr5YmYrHAf64ejM89S9h0wxredVzEN6uPsNNVqyZbbXDZBxDZETKPwJdXQVZK6V+/b6W5SW1GkrmK943TIbiEWXjBDeDyjwALrPocVk2u8Fsoj6S0LL5YXLrWoQL9YqvvekQKRCIiVcjc56wtVgv8uvYAS3aUfkPMXIeTF6abIermfk2JruOinesryfkdohg3yBw39dD3a1m/rwwh4ix+W3eA8fktT0+MaMt57SLBy4fOzaIKN7R9c9ZWl10PewBc+w0ERZnjf74bA468s79u9yL4dBScOA7R3WH0L6Vb16jZQBj0mHl/2v+ZLUxVbOK8HWTnOelSitahAgXjiNbtS6n4yudVTIFIRKSKtWsQwtU9Tu5z5nCWbguKr5YmsuNwBmEBdsYObF6ZJbrMA+e2YmCrCLLznNz+uWsGWa9MPM7936wGYHTvxtzYt8k/rtkSgJ/X7GfrobQKX69QcAO45mvw9oftf8L0f5e8fcj2P82p9Tlp0KQ/3PAj+NUp/fX6PwjNh0DeCfjmBsgq3dpQrpCUWvbWIYD6wb7E1gvEMGBxGcK+J1AgEhFxgwfPa0WwrxcbD6TyzbI9Zz0+NSuXN2aZCwveP7QFwb6etXDfmbh6kHXi0Uxu/XQ52XlOhrSux5Mj2532x7p9wxDObx+JYcD//nBhKxFAg05w2YeABZZ/DIvfK/64LdPNrrW8ExB7Llz3HfgEle1aVitc+oE5G+3Ydph6d7EBLCfPyd7jmWV+KyWZcErrUP9Stg4VKOg2W1DNus0UiERE3CAswM79+S0Zr87cQkpmyfuHxc9J4FhGDs0jArgmv3WpunDVIOuUzFxunLSUoxk5tGsQzFvXdD7jFhH3n9sSiwWmrz/o0q46wJwef95z5v0Zj5nh51Trf4Bvrjen/bcZCVdPBm+/8l0roC5cMclcS2njT+YebqdwOg1unLSUfi/N4YFvVrukmyopNYvJpZxZVpw+zc2B1X8nqIVIRERK4fpejWlRL5BjGTm8MfvMLRl7jmXyyYJdADx2QRu8bNXvP90VHWSdk+fk9i+Ws/1wBlEhvnw8pjsBPmdeW7hl/SBG5W8f4vJWIoDed0GX0YBhrpR9YK35+MrPzd+deeZGsZdPqvi2HzE94LznzfszHoe9ywuf+n7lXhbmB48pq/Zx7v/mM2PDwQpdrqB1qGvjOmVuHQLo1bwuVgvsOJLB/nLMpHSX6vdvlYhIDeFts/LkyLYAfLZoN9vOMN7llRlbyHE46dO8LoNb16vKEl2qvIOsDcPgkSlrWbzjGAF2Gx+P6U79YN+zvu7eIS2wWS3M3pzEykQXr4tjsZiLNjYdALkZ5gatc1+CqXcBBnS9ES6eYC4e6Qo974A2o8CZC9+OhsxjHM/IKZypeG3PRjSPCOBwWja3f76Cu75cydH07DJfpmjr0JlXpS5JsK83HaNDgeo120yBSETEjfq3iODctvVxOA2e/XUjxj/GiKzek8zUNfuxWDxvEcbyKM8g67dmJzBl5T5sVgvx13WhTVTpNsdtFhHIpZ3N/dQqpZXI5g1XfmauK5S6z1zNGszWowv/V/J+aWVlscBF8RDW3FzLaMptvDx9I8czc2lVP4hnRrVj2j39GTuwOTarhV/XHuC8/83n17X7T/tOleS9edsLW4cKxgKVR3Wcfq9AJCLiZv8Z0Qa7zcpf244wa1NS4eOGYfD8r+YijJd1ia68fcGqkM1q4c2rO9OklIOsf1y1l//lT59/9qJ2DGxVthaye4a0wNtm4a9tRypn1pNfqDkd398cN8OAh83urcoIrr7BZgDz8oWEPwhbFQ/Afy9pj7fNiq+3jYeHt+bHO/vQqn4QRzNyuOvLVdzxxQqS0rLOcnKzdejLJYkA3F+OsUOnOrlA49HiA5lhwMH1sPAtmP1cua/jSgpExdBeZiJSlRrXDeCW/k0BeH7aRrLzzH2gfl9/kOW7j+PrbeXB8zx3EcayCvHz5v1/dSMgf5D1+DMMsl6y4ygPfW+Ozbn9nGZc17OYlZ3PIibMn6u6xwDw+sytZWotKbWwZnDHQoybZpprB1VmK15kexznvwLAA17f8WjrJLo1CStySMfoUH65ux/3DGmBl9XCjA2HOO9/8/lx1d4S339B61C3xnXomx9oyqtLozr4els5nJbNtqR088GMI+Z+cD+Ohddaw4S+8McT5ia8uWcPbJVNgagY2stMRKrauEGx1A/2YffRTD5asJOcPCcv/m4Ghdv6NyMy5OxjZqqTlvWDeO1Kc5D1Rwt28uOqvUWe3344nds+X0Guw+D89pE8PLx1ua9116AW2L2sLN11rFKmgmfm5HHzlL30+zLjjOPAXOmTzH58mzcAm8Xg1qT/QuqB046xe1l54NyW/HxXX9o1CCY5M5f7v1nDLZ8u52DK6eHjUGoWk/Nbh8ozs+yffL1t9GocTA/LJk5MfwomDoBXYuGHm2HNl5B+ELz8zCUJhj5lDkJ3M4tRKXG5ZkhNTSUkJISUlBSCg0vXZy0iUl4/rtrL/d+swd9u44ZejZk4fwcRQT7MfXBgiTOqqrNXZ2zhnTkJ+HhZ+WFsH9o3DOFoejaXvPs3iccy6RQTyte39cLX21ah6zz7y0Y+XriTuJhQfrqzj8vGYmXlOrjl0+WFQatJXX9+HtePEP/KWSfqQMoJhr42D0dOJosjXiA0bRs07gv/mnrGAdy5DicT523nrdkJ5DicBPl68cSItlzRLbrwc3h66gYm/b2Lbo3r8N0dvcv/+RzbAQmzYfuf5CTMxe74x/pI9dtD88EQOwRieoF35QT98vz9ViAqgQKRiFQlwzC47L2/WZmYXPjYi5d2KFzVuiZyOA1u+XQZc7YcpmGoH9+P7c24yStZmZhMdB0/fhrXl/DACk5bBw6nZXPOy3M4kevgw391Y2jb+hU+Z06ek9s/X86cLYfxt9sI8fPmQEoW57SM4JMx3c+4RlJFjP1iBdPXH6Rr4zp8d3kE1g8GmSth9xoHve4wV9H29jfXPfpHqNl6KI1/f7eGNXvN2X39W4Tz4mUd8bJa6P/yHHLynEy+pWfh9hvFcjogJ+PkLTcDkveYq3Jv/xOO7yxy+FEjiEXEcf5F12FrMRiCIl3+mRRHgcjFFIhEpKqt3ZvMqHcWAtA6Mohp9/SvlD+sniTlRC4Xxy9k55EMAuw2MnIcBPt6MeXOPsTWK+PqziV46ffNvDd3O22igpl2dz+sFfhccx1O7vpyJTM2HMLX28qkG3sQ5OvFZe/9TVauk9vPacajF7RxWe0Ac7YkceMny8xZZHf3M2fbbfgJvhtdzNEWMxjZ88ORdwDY/XF6+7MnDTYcziXd6UOuzZeAwGAOp2TQOAjOjQ3EkpMBOemQm5kffNJPBqC8s4z1sXqZLT+xg3E2G0zXDw9x/ISDH8b2oWvjMmxbUkHl+ftdM9tgRUSqqY7RodzUtylfLNnNUyPb1fgwBPmDrG/oysXxC8nIceBltTDhhq4uDUNgjsX6fNFuNh1I5fcNB7mgQ1S5zuNwGtz/zWpmbDiE3cvKh//qTq9m5iDkV6+I464vVzFx/g7aNgjmok4NXVJ7Vq6Dp342N3i9sU+Tk0sPtLsYjj8Di96B7LRTAothtt7kZhQ5jxVoDDS2cnIUcQZmGjgBrCtlQRYr2APNTW/96pjdds0HQ9P+hVuUWIHesSv4bd1BFiYcqdJAVB5qISqBWohExB0MwyDXYWD3ql3zXuZsSeLVGVu4Y0BzRuavMu1q//tjK2/O3kZsvUBm3HdOmQOn02nw4PdrmLJyH942CxNv6Mrg1kW7317+fTPvzt2Oj5eV7+/oQ4foii+X8NrMLbz9ZwKRwb7M+r8BBJ5pTJnTAbknTrbu5GZCTmZ+ODpR5DFnTgZrd+xn7c791K8TyHmdmmMpCDlFboH5rU359+3+5tT/UowzmrxkN4//uJ4eTcP49vbeFf4cSkstRCIiNYDFYsHuVfNbhv5pUKt6DCrjOkNldXP/pkz6excJSelMXbOPSzpHl/q1hmHw+E/rCxeJfPuazqeFIYD/O68Vmw+m8efmJG77fDlT7+pHRFD5x0FtP5zOxHk7AHhqZNszhyEAqw18As3bWViBTudAR6fZLmKphNbIvs3N8UirEo+TmZOHv91zY0ft+t8PERGp1YJ9vbntnGYAvDlrG7klLAp5KsMweOaXjXy1NBGrBf53VSeGty++y81mtfDG1Z1oFhHAgZQs7py8gpy80l2nuOs++fN6chxOBraKYHh71w9KtlotFRpPVZLGdf1pGOpHrsNg6c5jlXINV1EgEhGRWmVMnybUDbCz62gmU1buPevxhmHw4vTNTPp7FwAvXx5XuHHsmQT7evPBv7oR5OPFsl3HefqXDeWqdeqa/SxMOIqPl5VnR7Wvdlu3WCyWwkUe/95eCSuFu5ACkYiI1CoBPl6MHWhuMvvW7ITClcHP5H+ztjFxvtll9d9L2nN519J1szWPCOStazpjscCXSxL5YvHuMtWZmpXL89PMzVvvGhRLo7r+ZXq9pyiYxr9gm2fva6ZAJCIitc71vRpTP9iHfckn+HbZnjMeFz8ngbdmbwPgyQvblnn7kEGt6/HvYea2K09P3VCmbqPXZmzhcFo2zSICuG1AszJd15P0yR9HtPFAaqk283UXBSIREal1fL1t3DUoFoC3/0wgK/f0VqIP/9rBKzO2APDI+a25qV/Tcl1r7IDmXNgxijynwdgvVrAv+cRZX7Nubwqf57coPX9Re3y8KrZStztFBPnQOtKciv/3ds9tJVIgEhGRWunK7jE0DPUjKS37tO6szxfvLuyuun9oS+4Y0Lzc17FYLLxyeRztGgRzNCOH2z9fzomcM3fTOZwGj/+0DqcBF3VqQJ+SVo6uJgq6zRZWwl5yrqJAJCIitZKPl417hpitRO/N3U5GtrnB6LfL9vDET+sBuHNg88JjKsLPbmPiDV0JC7Czfl8qD/+w9ow7z3+5ZDdr96YQ5OPF4yNcu9q1uxQMrF6Y4LkDqxWIihEfH0/btm3p3r27u0sREZFKdGmXaJrU9edoRg6T/t7Fz6v38fCUtQDc1Lcp/x7WymUzu6Lr+PPudV3wslqYumY/7+cP1D5VUloWL+d30z04rBX1gipn89Oq1qNpXbysFhKPZbLnWObZX+AGCkTFGDduHBs3bmTZsmXuLkVERCqRt83KfUNbAuYA6ge+XYNhwPW9GvHEhW1cPs29V7O6PDWyLQAv/r6ZuVuSijz/wrRNpGXl0aFhCNf3KtsAbk8W6ONF50ahgOd2mykQiYhIrTYyrgEt6gWSmePA4TS4omt0pa75c32vxlzTIwbDgLu/WsWOw+kA/J1whJ9W78diMaf317R97Apmmy1QIBIREfE8NquFxy5og9UCl3WJ5sXLOlbays1gDrJ+ZlR7ujWuQ1pWHrd+tpyj6dn852dz3NL1PRvTMTq00q7vLv1amIFo0fajOJ2et42qNnctgTZ3FRGpPap6r62ktCxGvb2Qg6lZRAT5cDgtm/BAH2b/3wBC/LyrrI6qkpPnpNOzM8nMcfDbPf1p26Dy/q6W5++3WohERESgyjcerRfky/v/6oqPl5XDadkA/GdEmxoZhgDsXlZ6Ng0DPHMckQKRiIiIm3SMDuWlyzpiscA5LSO4qFPJe6RVd4XrEXngAo1VG4dFRESkiIs7N6R70zDqBtir3eatZVUQiJbsOEZOnhO7l+e0y3hOJSIiIrVUw1A/fL2r7/YcpdWqfhDhgXZO5DpYvSfZ3eUUoUAkIiIiVcJqtdDbQ6ffKxCJiIhIlemXv43H3wpEIiIiUlsVjCNatSeZtKxcN1dzkgKRiIiIVJnoOv40ruuPw2mwdOcxd5dTSIFIREREqlTh9PuEo26u5CQFIhEREalSfZsXBCLPGUekQCQiIiJVqnfzulgssOVQGklpWe4uB1AgEhERkSoWFmCnXf5eZou2e0a3mQKRiIiIVDlP6zZTIBIREZEqVzCwesG2IxiG4eZqFIhERETEDbo3CcNus+Jrt5Gc6f71iLS5azHi4+OJj4/H4XC4uxQREZEayc9uY/FjQwgLsLu7FAAshie0U3mo1NRUQkJCSElJITg42N3liIiISCmU5++3usxERESk1lMgEhERkVpPgUhERERqPQUiERERqfUUiERERKTWUyASERGRWk+BSERERGo9BSIRERGp9RSIREREpNZTIBIREZFaT4FIREREaj0FIhEREan1FIhERESk1vNydwGezDAMwNw1V0RERKqHgr/bBX/HS0OBqARpaWkAxMTEuLkSERERKau0tDRCQkJKdazFKEt8qmWcTif79+8nKCgIi8Xi0nOnpqYSExPDnj17CA4Odum5azJ9bmWnz6x89LmVjz638tHnVnYlfWaGYZCWlkaDBg2wWks3OkgtRCWwWq1ER0dX6jWCg4P15S8HfW5lp8+sfPS5lY8+t/LR51Z2Z/rMStsyVECDqkVERKTWUyASERGRWk+ByE18fHx46qmn8PHxcXcp1Yo+t7LTZ1Y++tzKR59b+ehzKztXf2YaVC0iIiK1nlqIREREpNZTIBIREZFaT4FIREREaj0FIhEREan1FIjcJD4+niZNmuDr60vPnj1ZunSpu0vyWE8//TQWi6XIrXXr1u4uy+PMnz+fkSNH0qBBAywWCz/99FOR5w3D4MknnyQqKgo/Pz+GDh3Ktm3b3FOsBznb5zZmzJjTvn/Dhw93T7EeYvz48XTv3p2goCDq1avHxRdfzJYtW4ock5WVxbhx46hbty6BgYFcdtllHDp0yE0Ve4bSfG4DBw487ft2xx13uKliz/Dee+/RsWPHwgUYe/fuzfTp0wufd9V3TYHIDb755hseeOABnnrqKVauXElcXBzDhg0jKSnJ3aV5rHbt2nHgwIHC24IFC9xdksfJyMggLi6O+Pj4Yp9/+eWXeeutt5gwYQJLliwhICCAYcOGkZWVVcWVepazfW4Aw4cPL/L9++qrr6qwQs8zb948xo0bx+LFi/njjz/Izc3lvPPOIyMjo/CY+++/n19++YXvvvuOefPmsX//fi699FI3Vu1+pfncAG699dYi37eXX37ZTRV7hujoaF588UVWrFjB8uXLGTx4MBdddBEbNmwAXPhdM6TK9ejRwxg3blzh7w6Hw2jQoIExfvx4N1bluZ566ikjLi7O3WVUK4Dx448/Fv7udDqNyMhI45VXXil8LDk52fDx8TG++uorN1Tomf75uRmGYYwePdq46KKL3FJPdZGUlGQAxrx58wzDML9b3t7exnfffVd4zKZNmwzAWLRokbvK9Dj//NwMwzAGDBhg3Hvvve4rqpqoU6eO8eGHH7r0u6YWoiqWk5PDihUrGDp0aOFjVquVoUOHsmjRIjdW5tm2bdtGgwYNaNasGddddx2JiYnuLqla2blzJwcPHizyvQsJCaFnz5763pXC3LlzqVevHq1atWLs2LEcPXrU3SV5lJSUFADCwsIAWLFiBbm5uUW+b61bt6ZRo0b6vp3in59bgcmTJxMeHk779u159NFHyczMdEd5HsnhcPD111+TkZFB7969Xfpd0+auVezIkSM4HA7q169f5PH69euzefNmN1Xl2Xr27MmkSZNo1aoVBw4c4JlnnqF///6sX7+eoKAgd5dXLRw8eBCg2O9dwXNSvOHDh3PppZfStGlTtm/fzmOPPcb555/PokWLsNls7i7P7ZxOJ/fddx99+/alffv2gPl9s9vthIaGFjlW37eTivvcAK699loaN25MgwYNWLt2LQ8//DBbtmxhypQpbqzW/datW0fv3r3JysoiMDCQH3/8kbZt27J69WqXfdcUiMTjnX/++YX3O3bsSM+ePWncuDHffvstN998sxsrk9rg6quvLrzfoUMHOnbsSPPmzZk7dy5DhgxxY2WeYdy4caxfv17j+sroTJ/bbbfdVni/Q4cOREVFMWTIELZv307z5s2rukyP0apVK1avXk1KSgrff/89o0ePZt68eS69hrrMqlh4eDg2m+20EfCHDh0iMjLSTVVVL6GhobRs2ZKEhAR3l1JtFHy39L2ruGbNmhEeHq7vH3DXXXfx66+/MmfOHKKjowsfj4yMJCcnh+Tk5CLH6/tmOtPnVpyePXsC1Prvm91uJzY2lq5duzJ+/Hji4uJ48803XfpdUyCqYna7na5duzJ79uzCx5xOJ7Nnz6Z3795urKz6SE9PZ/v27URFRbm7lGqjadOmREZGFvnepaamsmTJEn3vymjv3r0cPXq0Vn//DMPgrrvu4scff+TPP/+kadOmRZ7v2rUr3t7eRb5vW7ZsITExsVZ/3872uRVn9erVALX6+1Ycp9NJdna2S79r6jJzgwceeIDRo0fTrVs3evTowRtvvEFGRgY33niju0vzSA8++CAjR46kcePG7N+/n6eeegqbzcY111zj7tI8Snp6epH/i9y5cyerV68mLCyMRo0acd999/H888/TokULmjZtyhNPPEGDBg24+OKL3Ve0ByjpcwsLC+OZZ57hsssuIzIyku3bt/PQQw8RGxvLsGHD3Fi1e40bN44vv/ySn3/+maCgoMKxGiEhIfj5+RESEsLNN9/MAw88QFhYGMHBwdx999307t2bXr16ubl69znb57Z9+3a+/PJLLrjgAurWrcvatWu5//77Oeecc+jYsaObq3efRx99lPPPP59GjRqRlpbGl19+ydy5c5kxY4Zrv2uunQgnpfX2228bjRo1Mux2u9GjRw9j8eLF7i7JY1111VVGVFSUYbfbjYYNGxpXXXWVkZCQ4O6yPM6cOXMM4LTb6NGjDcMwp94/8cQTRv369Q0fHx9jyJAhxpYtW9xbtAco6XPLzMw0zjvvPCMiIsLw9vY2GjdubNx6663GwYMH3V22WxX3eQHGJ598UnjMiRMnjDvvvNOoU6eO4e/vb1xyySXGgQMH3Fe0Bzjb55aYmGicc845RlhYmOHj42PExsYa//73v42UlBT3Fu5mN910k9G4cWPDbrcbERERxpAhQ4yZM2cWPu+q75rFMAyjoulNREREpDrTGCIRERGp9RSIREREpNZTIBIREZFaT4FIREREaj0FIhEREan1FIhERESk1lMgEhERkVpPgUhEpAzmzp2LxWI5be8kEaneFIhERESk1lMgEhERkVpPgUhEqhWn08n48eNp2rQpfn5+xMXF8f333wMnu7OmTZtGx44d8fX1pVevXqxfv77IOX744QfatWuHj48PTZo04bXXXivyfHZ2Ng8//DAxMTH4+PgQGxvLRx99VOSYFStW0K1bN/z9/enTpw9btmyp3DcuIpVKgUhEqpXx48fz2WefMWHCBDZs2MD999/P9ddfz7x58wqP+fe//81rr73GsmXLiIiIYOTIkeTm5gJmkLnyyiu5+uqrWbduHU8//TRPPPEEkyZNKnz9v/71L7766iveeustNm3axMSJEwkMDCxSx+OPP85rr73G8uXL8fLy4qabbqqS9y8ilUObu4pItZGdnU1YWBizZs2id+/ehY/fcsstZGZmcttttzFo0CC+/vprrrrqKgCOHTtGdHQ0kyZN4sorr+S6667j8OHDzJw5s/D1Dz30ENOmTWPDhg1s3bqVVq1a8ccffzB06NDTapg7dy6DBg1i1qxZDBkyBIDffvuNESNGcOLECXx9fSv5UxCRyqAWIhGpNhISEsjMzOTcc88lMDCw8PbZZ5+xffv2wuNODUthYWG0atWKTZs2AbBp0yb69u1b5Lx9+/Zl27ZtOBwOVq9ejc1mY8CAASXW0rFjx8L7UVFRACQlJVX4PYqIe3i5uwARkdJKT08HYNq0aTRs2LDIcz4+PkVCUXn5+fmV6jhvb+/C+xaLBTDHN4lI9aQWIhGpNtq2bYuPjw+JiYnExsYWucXExBQet3jx4sL7x48fZ+vWrbRp0waANm3asHDhwiLnXbhwIS1btsRms9GhQwecTmeRMUkiUvOphUhEqo2goCAefPBB7r//fpxOJ/369SMlJYWFCxcSHBxM48aNAXj22WepW7cu9evX5/HHHyc8PJyLL74YgP/7v/+je/fuPPfcc1x11VUsWrSId955h3fffReAJk2aMHr0aG666Sbeeust4uLi2L17N0lJSVx55ZXueusiUskUiESkWnnuueeIiIhg/Pjx7Nixg9DQULp06cJjjz1W2GX14osvcu+997Jt2zY6derEL7/8gt1uB6BLly58++23PPnkkzz33HNERUXx7LPPMmbMmMJrvPfeezz22GPceeedHD16lEaNGvHYY4+54+2KSBXRLDMRqTEKZoAdP36c0NBQd5cjItWIxhCJiIhIradAJCIiIrWeusxERESk1lMLkYiIiNR6CkQiIiJS6ykQiYiISK2nQCQiIiK1ngKRiIiI1HoKRCIiIlLrKRCJiIhIradAJCIiIrWeApGIiIjUev8PgV09zmDd4+oAAAAASUVORK5CYII=",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -388,7 +467,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -396,2020 +475,1275 @@
      "output_type": "stream",
      "text": [
       "Epoch 1/1000\n",
-      " 14/218 [>.............................] - ETA: 1s - loss: 0.4354 - accuracy: 0.6429"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\Muell\\AppData\\Local\\Temp\\ipykernel_6032\\1608076191.py:11: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n",
-      "  history = model.fit_generator(train_iterator, validation_data = validation_iterator, epochs = Epoch_Anz)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.3309 - accuracy: 0.7188 - val_loss: 0.2077 - val_accuracy: 0.7241\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.7114 - loss: 0.3507 - val_accuracy: 0.8851 - val_loss: 0.1360\n",
       "Epoch 2/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.1626 - accuracy: 0.8350 - val_loss: 0.1460 - val_accuracy: 0.8506\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.8718 - loss: 0.1377 - val_accuracy: 0.8966 - val_loss: 0.0787\n",
       "Epoch 3/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0990 - accuracy: 0.8890 - val_loss: 0.0708 - val_accuracy: 0.9310\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9167 - loss: 0.0777 - val_accuracy: 0.9425 - val_loss: 0.0730\n",
       "Epoch 4/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0703 - accuracy: 0.9132 - val_loss: 0.0564 - val_accuracy: 0.9310\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9355 - loss: 0.0548 - val_accuracy: 0.9310 - val_loss: 0.0627\n",
       "Epoch 5/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0663 - accuracy: 0.9206 - val_loss: 0.0681 - val_accuracy: 0.9310\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9271 - loss: 0.0574 - val_accuracy: 0.9540 - val_loss: 0.0454\n",
       "Epoch 6/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0575 - accuracy: 0.9275 - val_loss: 0.0359 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9305 - loss: 0.0460 - val_accuracy: 0.9425 - val_loss: 0.0398\n",
       "Epoch 7/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0503 - accuracy: 0.9321 - val_loss: 0.0733 - val_accuracy: 0.9425\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9530 - loss: 0.0362 - val_accuracy: 0.9770 - val_loss: 0.0250\n",
       "Epoch 8/1000\n",
-      "218/218 [==============================] - 3s 11ms/step - loss: 0.0399 - accuracy: 0.9482 - val_loss: 0.0423 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9425 - loss: 0.0453 - val_accuracy: 0.9080 - val_loss: 0.0322\n",
       "Epoch 9/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0390 - accuracy: 0.9454 - val_loss: 0.0594 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9459 - loss: 0.0299 - val_accuracy: 0.9425 - val_loss: 0.0267\n",
       "Epoch 10/1000\n",
-      "218/218 [==============================] - 3s 12ms/step - loss: 0.0369 - accuracy: 0.9482 - val_loss: 0.0279 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9497 - loss: 0.0248 - val_accuracy: 0.9425 - val_loss: 0.0326\n",
       "Epoch 11/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0339 - accuracy: 0.9505 - val_loss: 0.0236 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9608 - loss: 0.0229 - val_accuracy: 0.9655 - val_loss: 0.0192\n",
       "Epoch 12/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0260 - accuracy: 0.9517 - val_loss: 0.0265 - val_accuracy: 0.9540\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9619 - loss: 0.0194 - val_accuracy: 1.0000 - val_loss: 0.0171\n",
       "Epoch 13/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0266 - accuracy: 0.9517 - val_loss: 0.0273 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9603 - loss: 0.0175 - val_accuracy: 0.9885 - val_loss: 0.0157\n",
       "Epoch 14/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0282 - accuracy: 0.9586 - val_loss: 0.0155 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9634 - loss: 0.0162 - val_accuracy: 0.9770 - val_loss: 0.0126\n",
       "Epoch 15/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0236 - accuracy: 0.9523 - val_loss: 0.0126 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9672 - loss: 0.0151 - val_accuracy: 0.9540 - val_loss: 0.0140\n",
       "Epoch 16/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0198 - accuracy: 0.9603 - val_loss: 0.0448 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9618 - loss: 0.0141 - val_accuracy: 0.9770 - val_loss: 0.0134\n",
       "Epoch 17/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0173 - accuracy: 0.9626 - val_loss: 0.0119 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9701 - loss: 0.0147 - val_accuracy: 0.9770 - val_loss: 0.0088\n",
       "Epoch 18/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0250 - accuracy: 0.9551 - val_loss: 0.0114 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step - accuracy: 0.9767 - loss: 0.0142 - val_accuracy: 0.9655 - val_loss: 0.0130\n",
       "Epoch 19/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0155 - accuracy: 0.9626 - val_loss: 0.0206 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9675 - loss: 0.0128 - val_accuracy: 0.9770 - val_loss: 0.0094\n",
       "Epoch 20/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0153 - accuracy: 0.9643 - val_loss: 0.0114 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9692 - loss: 0.0105 - val_accuracy: 0.9770 - val_loss: 0.0086\n",
       "Epoch 21/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0143 - accuracy: 0.9735 - val_loss: 0.0108 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9625 - loss: 0.0134 - val_accuracy: 1.0000 - val_loss: 0.0131\n",
       "Epoch 22/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0155 - accuracy: 0.9661 - val_loss: 0.0109 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9690 - loss: 0.0114 - val_accuracy: 0.9770 - val_loss: 0.0039\n",
       "Epoch 23/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0144 - accuracy: 0.9649 - val_loss: 0.0082 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9745 - loss: 0.0087 - val_accuracy: 0.9655 - val_loss: 0.0092\n",
       "Epoch 24/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0137 - accuracy: 0.9730 - val_loss: 0.0199 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9703 - loss: 0.0087 - val_accuracy: 0.9655 - val_loss: 0.0087\n",
       "Epoch 25/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0137 - accuracy: 0.9689 - val_loss: 0.0078 - val_accuracy: 0.9540\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9782 - loss: 0.0106 - val_accuracy: 0.9540 - val_loss: 0.0063\n",
       "Epoch 26/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0109 - accuracy: 0.9735 - val_loss: 0.0156 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9737 - loss: 0.0091 - val_accuracy: 0.9540 - val_loss: 0.0073\n",
       "Epoch 27/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0123 - accuracy: 0.9707 - val_loss: 0.0074 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9747 - loss: 0.0092 - val_accuracy: 0.9885 - val_loss: 0.0061\n",
       "Epoch 28/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0108 - accuracy: 0.9689 - val_loss: 0.0079 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9658 - loss: 0.0095 - val_accuracy: 0.9655 - val_loss: 0.0145\n",
       "Epoch 29/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0111 - accuracy: 0.9730 - val_loss: 0.0094 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9800 - loss: 0.0092 - val_accuracy: 0.9540 - val_loss: 0.0114\n",
       "Epoch 30/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0127 - accuracy: 0.9678 - val_loss: 0.0146 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9678 - loss: 0.0086 - val_accuracy: 1.0000 - val_loss: 0.0072\n",
       "Epoch 31/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0095 - accuracy: 0.9735 - val_loss: 0.0052 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9665 - loss: 0.0073 - val_accuracy: 0.9770 - val_loss: 0.0033\n",
       "Epoch 32/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0091 - accuracy: 0.9753 - val_loss: 0.0066 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9741 - loss: 0.0064 - val_accuracy: 0.9655 - val_loss: 0.0081\n",
       "Epoch 33/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0109 - accuracy: 0.9718 - val_loss: 0.0072 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9746 - loss: 0.0058 - val_accuracy: 0.9770 - val_loss: 0.0061\n",
       "Epoch 34/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0089 - accuracy: 0.9758 - val_loss: 0.0050 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9740 - loss: 0.0069 - val_accuracy: 0.9540 - val_loss: 0.0148\n",
       "Epoch 35/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0091 - accuracy: 0.9724 - val_loss: 0.0071 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9831 - loss: 0.0075 - val_accuracy: 0.9770 - val_loss: 0.0052\n",
       "Epoch 36/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0093 - accuracy: 0.9741 - val_loss: 0.0067 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9801 - loss: 0.0052 - val_accuracy: 0.9540 - val_loss: 0.0075\n",
       "Epoch 37/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0076 - accuracy: 0.9747 - val_loss: 0.0049 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9756 - loss: 0.0060 - val_accuracy: 0.9770 - val_loss: 0.0039\n",
       "Epoch 38/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0096 - accuracy: 0.9730 - val_loss: 0.0077 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9748 - loss: 0.0060 - val_accuracy: 0.9540 - val_loss: 0.0059\n",
       "Epoch 39/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0072 - accuracy: 0.9804 - val_loss: 0.0090 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9706 - loss: 0.0052 - val_accuracy: 1.0000 - val_loss: 0.0044\n",
       "Epoch 40/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0077 - accuracy: 0.9741 - val_loss: 0.0062 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9790 - loss: 0.0047 - val_accuracy: 0.9655 - val_loss: 0.0067\n",
       "Epoch 41/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0077 - accuracy: 0.9776 - val_loss: 0.0058 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9765 - loss: 0.0062 - val_accuracy: 0.9655 - val_loss: 0.0039\n",
       "Epoch 42/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0081 - accuracy: 0.9712 - val_loss: 0.0085 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9705 - loss: 0.0057 - val_accuracy: 0.9885 - val_loss: 0.0057\n",
       "Epoch 43/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0087 - accuracy: 0.9770 - val_loss: 0.0030 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9786 - loss: 0.0055 - val_accuracy: 0.9540 - val_loss: 0.0053\n",
       "Epoch 44/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0069 - accuracy: 0.9758 - val_loss: 0.0110 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9747 - loss: 0.0052 - val_accuracy: 0.9540 - val_loss: 0.0042\n",
       "Epoch 45/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0077 - accuracy: 0.9707 - val_loss: 0.0057 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9809 - loss: 0.0053 - val_accuracy: 0.9885 - val_loss: 0.0044\n",
       "Epoch 46/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0064 - accuracy: 0.9689 - val_loss: 0.0050 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9704 - loss: 0.0056 - val_accuracy: 0.9540 - val_loss: 0.0077\n",
       "Epoch 47/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0070 - accuracy: 0.9804 - val_loss: 0.0037 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9725 - loss: 0.0050 - val_accuracy: 0.9885 - val_loss: 0.0037\n",
       "Epoch 48/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0078 - accuracy: 0.9730 - val_loss: 0.0060 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9833 - loss: 0.0051 - val_accuracy: 0.9770 - val_loss: 0.0044\n",
       "Epoch 49/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0079 - accuracy: 0.9776 - val_loss: 0.0028 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9820 - loss: 0.0057 - val_accuracy: 0.9885 - val_loss: 0.0045\n",
       "Epoch 50/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0081 - accuracy: 0.9787 - val_loss: 0.0082 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9741 - loss: 0.0057 - val_accuracy: 0.9770 - val_loss: 0.0052\n",
       "Epoch 51/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0064 - accuracy: 0.9770 - val_loss: 0.0037 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9755 - loss: 0.0055 - val_accuracy: 0.9770 - val_loss: 0.0057\n",
       "Epoch 52/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0059 - accuracy: 0.9741 - val_loss: 0.0065 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9787 - loss: 0.0045 - val_accuracy: 1.0000 - val_loss: 0.0040\n",
       "Epoch 53/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0069 - accuracy: 0.9747 - val_loss: 0.0034 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9826 - loss: 0.0044 - val_accuracy: 0.9885 - val_loss: 0.0052\n",
       "Epoch 54/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0061 - accuracy: 0.9810 - val_loss: 0.0036 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9866 - loss: 0.0041 - val_accuracy: 0.9655 - val_loss: 0.0055\n",
       "Epoch 55/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0057 - accuracy: 0.9781 - val_loss: 0.0049 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9759 - loss: 0.0070 - val_accuracy: 0.9885 - val_loss: 0.0051\n",
       "Epoch 56/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0056 - accuracy: 0.9850 - val_loss: 0.0037 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9756 - loss: 0.0046 - val_accuracy: 0.9770 - val_loss: 0.0029\n",
       "Epoch 57/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0052 - accuracy: 0.9764 - val_loss: 0.0033 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9807 - loss: 0.0038 - val_accuracy: 0.9885 - val_loss: 0.0049\n",
       "Epoch 58/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0055 - accuracy: 0.9758 - val_loss: 0.0034 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9789 - loss: 0.0041 - val_accuracy: 0.9885 - val_loss: 0.0030\n",
       "Epoch 59/1000\n",
-      "218/218 [==============================] - 3s 11ms/step - loss: 0.0064 - accuracy: 0.9741 - val_loss: 0.0038 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9684 - loss: 0.0049 - val_accuracy: 0.9770 - val_loss: 0.0036\n",
       "Epoch 60/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0047 - accuracy: 0.9839 - val_loss: 0.0035 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9806 - loss: 0.0046 - val_accuracy: 0.9655 - val_loss: 0.0026\n",
       "Epoch 61/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0050 - accuracy: 0.9781 - val_loss: 0.0035 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9799 - loss: 0.0046 - val_accuracy: 0.9885 - val_loss: 0.0049\n",
       "Epoch 62/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0052 - accuracy: 0.9770 - val_loss: 0.0028 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9818 - loss: 0.0036 - val_accuracy: 0.9310 - val_loss: 0.0036\n",
       "Epoch 63/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0052 - accuracy: 0.9730 - val_loss: 0.0031 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9809 - loss: 0.0042 - val_accuracy: 0.9655 - val_loss: 0.0045\n",
       "Epoch 64/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0051 - accuracy: 0.9764 - val_loss: 0.0041 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9810 - loss: 0.0033 - val_accuracy: 0.9770 - val_loss: 0.0035\n",
       "Epoch 65/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0073 - accuracy: 0.9781 - val_loss: 0.0023 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9825 - loss: 0.0040 - val_accuracy: 0.9655 - val_loss: 0.0035\n",
       "Epoch 66/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0046 - accuracy: 0.9822 - val_loss: 0.0032 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9824 - loss: 0.0044 - val_accuracy: 0.9885 - val_loss: 0.0047\n",
       "Epoch 67/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0048 - accuracy: 0.9770 - val_loss: 0.0034 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9844 - loss: 0.0044 - val_accuracy: 0.9540 - val_loss: 0.0047\n",
       "Epoch 68/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0049 - accuracy: 0.9753 - val_loss: 0.0031 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - accuracy: 0.9809 - loss: 0.0033 - val_accuracy: 1.0000 - val_loss: 0.0028\n",
       "Epoch 69/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0045 - accuracy: 0.9850 - val_loss: 0.0035 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9835 - loss: 0.0037 - val_accuracy: 0.9655 - val_loss: 0.0028\n",
       "Epoch 70/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0045 - accuracy: 0.9868 - val_loss: 0.0025 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 9ms/step - accuracy: 0.9769 - loss: 0.0041 - val_accuracy: 0.9540 - val_loss: 0.0061\n",
       "Epoch 71/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0049 - accuracy: 0.9822 - val_loss: 0.0035 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9758 - loss: 0.0033 - val_accuracy: 0.9770 - val_loss: 0.0059\n",
       "Epoch 72/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0047 - accuracy: 0.9747 - val_loss: 0.0037 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - accuracy: 0.9821 - loss: 0.0032 - val_accuracy: 0.9885 - val_loss: 0.0029\n",
       "Epoch 73/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0038 - accuracy: 0.9873 - val_loss: 0.0028 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9833 - loss: 0.0033 - val_accuracy: 0.9885 - val_loss: 0.0028\n",
       "Epoch 74/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0052 - accuracy: 0.9770 - val_loss: 0.0032 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - accuracy: 0.9830 - loss: 0.0028 - val_accuracy: 1.0000 - val_loss: 0.0035\n",
       "Epoch 75/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0048 - accuracy: 0.9810 - val_loss: 0.0031 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - accuracy: 0.9887 - loss: 0.0031 - val_accuracy: 1.0000 - val_loss: 0.0042\n",
       "Epoch 76/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0042 - accuracy: 0.9845 - val_loss: 0.0034 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9838 - loss: 0.0034 - val_accuracy: 0.9655 - val_loss: 0.0026\n",
       "Epoch 77/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0043 - accuracy: 0.9816 - val_loss: 0.0037 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9832 - loss: 0.0029 - val_accuracy: 1.0000 - val_loss: 0.0025\n",
       "Epoch 78/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0040 - accuracy: 0.9816 - val_loss: 0.0035 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9855 - loss: 0.0028 - val_accuracy: 0.9885 - val_loss: 0.0046\n",
       "Epoch 79/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0042 - accuracy: 0.9822 - val_loss: 0.0028 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - accuracy: 0.9815 - loss: 0.0031 - val_accuracy: 0.9885 - val_loss: 0.0046\n",
       "Epoch 80/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0042 - accuracy: 0.9833 - val_loss: 0.0034 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9818 - loss: 0.0034 - val_accuracy: 0.9540 - val_loss: 0.0026\n",
       "Epoch 81/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0036 - accuracy: 0.9879 - val_loss: 0.0033 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9826 - loss: 0.0034 - val_accuracy: 0.9885 - val_loss: 0.0029\n",
       "Epoch 82/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0041 - accuracy: 0.9839 - val_loss: 0.0027 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9805 - loss: 0.0026 - val_accuracy: 0.9885 - val_loss: 0.0022\n",
       "Epoch 83/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0039 - accuracy: 0.9799 - val_loss: 0.0032 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9829 - loss: 0.0033 - val_accuracy: 0.9885 - val_loss: 0.0027\n",
       "Epoch 84/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0041 - accuracy: 0.9868 - val_loss: 0.0033 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9796 - loss: 0.0029 - val_accuracy: 0.9770 - val_loss: 0.0019\n",
       "Epoch 85/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0035 - accuracy: 0.9839 - val_loss: 0.0025 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9822 - loss: 0.0025 - val_accuracy: 0.9885 - val_loss: 0.0022\n",
       "Epoch 86/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0041 - accuracy: 0.9787 - val_loss: 0.0028 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9793 - loss: 0.0032 - val_accuracy: 0.9885 - val_loss: 0.0040\n",
       "Epoch 87/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0036 - accuracy: 0.9827 - val_loss: 0.0028 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9802 - loss: 0.0027 - val_accuracy: 0.9885 - val_loss: 0.0022\n",
       "Epoch 88/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0035 - accuracy: 0.9850 - val_loss: 0.0028 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9804 - loss: 0.0030 - val_accuracy: 0.9770 - val_loss: 0.0031\n",
       "Epoch 89/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0037 - accuracy: 0.9770 - val_loss: 0.0025 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9801 - loss: 0.0030 - val_accuracy: 0.9770 - val_loss: 0.0028\n",
       "Epoch 90/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0037 - accuracy: 0.9799 - val_loss: 0.0031 - val_accuracy: 0.9655\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9849 - loss: 0.0023 - val_accuracy: 0.9885 - val_loss: 0.0027\n",
       "Epoch 91/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0040 - accuracy: 0.9787 - val_loss: 0.0023 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9885 - loss: 0.0026 - val_accuracy: 0.9770 - val_loss: 0.0025\n",
       "Epoch 92/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0029 - accuracy: 0.9810 - val_loss: 0.0029 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9857 - loss: 0.0035 - val_accuracy: 0.9770 - val_loss: 0.0018\n",
       "Epoch 93/1000\n",
-      "218/218 [==============================] - 2s 11ms/step - loss: 0.0035 - accuracy: 0.9839 - val_loss: 0.0016 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9848 - loss: 0.0022 - val_accuracy: 0.9770 - val_loss: 0.0028\n",
       "Epoch 94/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0034 - accuracy: 0.9804 - val_loss: 0.0032 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9796 - loss: 0.0024 - val_accuracy: 0.9770 - val_loss: 0.0017\n",
       "Epoch 95/1000\n",
-      "218/218 [==============================] - 2s 10ms/step - loss: 0.0038 - accuracy: 0.9793 - val_loss: 0.0029 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9861 - loss: 0.0025 - val_accuracy: 1.0000 - val_loss: 0.0018\n",
       "Epoch 96/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 0.0037 - accuracy: 0.9799 - val_loss: 0.0037 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9788 - loss: 0.0023 - val_accuracy: 1.0000 - val_loss: 0.0018\n",
       "Epoch 97/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0035 - accuracy: 0.9758 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9841 - loss: 0.0028 - val_accuracy: 0.9770 - val_loss: 0.0018\n",
       "Epoch 98/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0032 - accuracy: 0.9862 - val_loss: 0.0034 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9844 - loss: 0.0022 - val_accuracy: 0.9885 - val_loss: 0.0032\n",
       "Epoch 99/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0037 - accuracy: 0.9833 - val_loss: 0.0018 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9909 - loss: 0.0025 - val_accuracy: 1.0000 - val_loss: 0.0017\n",
       "Epoch 100/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0029 - accuracy: 0.9850 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9853 - loss: 0.0023 - val_accuracy: 0.9655 - val_loss: 0.0021\n",
       "Epoch 101/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0035 - accuracy: 0.9839 - val_loss: 0.0034 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9882 - loss: 0.0023 - val_accuracy: 1.0000 - val_loss: 0.0033\n",
       "Epoch 102/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0034 - accuracy: 0.9816 - val_loss: 0.0042 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9819 - loss: 0.0023 - val_accuracy: 0.9655 - val_loss: 0.0025\n",
       "Epoch 103/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0030 - accuracy: 0.9816 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9878 - loss: 0.0027 - val_accuracy: 1.0000 - val_loss: 0.0031\n",
       "Epoch 104/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0033 - accuracy: 0.9873 - val_loss: 0.0029 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9916 - loss: 0.0023 - val_accuracy: 0.9770 - val_loss: 0.0017\n",
       "Epoch 105/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0031 - accuracy: 0.9822 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 7ms/step - accuracy: 0.9863 - loss: 0.0021 - val_accuracy: 0.9655 - val_loss: 0.0024\n",
       "Epoch 106/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0033 - accuracy: 0.9827 - val_loss: 0.0023 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9803 - loss: 0.0024 - val_accuracy: 0.9770 - val_loss: 0.0034\n",
       "Epoch 107/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0030 - accuracy: 0.9827 - val_loss: 0.0025 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9829 - loss: 0.0020 - val_accuracy: 0.9885 - val_loss: 0.0026\n",
       "Epoch 108/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0028 - accuracy: 0.9822 - val_loss: 0.0023 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9784 - loss: 0.0023 - val_accuracy: 0.9885 - val_loss: 0.0018\n",
       "Epoch 109/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0027 - accuracy: 0.9787 - val_loss: 0.0026 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9865 - loss: 0.0021 - val_accuracy: 0.9770 - val_loss: 0.0020\n",
       "Epoch 110/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9833 - val_loss: 0.0026 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9858 - loss: 0.0024 - val_accuracy: 0.9885 - val_loss: 0.0023\n",
       "Epoch 111/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0031 - accuracy: 0.9873 - val_loss: 0.0027 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9864 - loss: 0.0022 - val_accuracy: 0.9885 - val_loss: 0.0020\n",
       "Epoch 112/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0033 - accuracy: 0.9799 - val_loss: 0.0039 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9865 - loss: 0.0021 - val_accuracy: 0.9885 - val_loss: 0.0015\n",
       "Epoch 113/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0032 - accuracy: 0.9833 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9890 - loss: 0.0021 - val_accuracy: 0.9655 - val_loss: 0.0020\n",
       "Epoch 114/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0028 - accuracy: 0.9804 - val_loss: 0.0028 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9874 - loss: 0.0021 - val_accuracy: 1.0000 - val_loss: 0.0027\n",
       "Epoch 115/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0031 - accuracy: 0.9839 - val_loss: 0.0027 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9886 - loss: 0.0019 - val_accuracy: 0.9885 - val_loss: 0.0019\n",
       "Epoch 116/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0029 - accuracy: 0.9850 - val_loss: 0.0025 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9833 - loss: 0.0024 - val_accuracy: 0.9885 - val_loss: 0.0019\n",
       "Epoch 117/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9879 - val_loss: 0.0021 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9844 - loss: 0.0019 - val_accuracy: 0.9885 - val_loss: 0.0019\n",
       "Epoch 118/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0026 - accuracy: 0.9850 - val_loss: 0.0021 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9819 - loss: 0.0022 - val_accuracy: 0.9885 - val_loss: 0.0015\n",
       "Epoch 119/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9850 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9786 - loss: 0.0023 - val_accuracy: 1.0000 - val_loss: 0.0015\n",
       "Epoch 120/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9845 - val_loss: 0.0019 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9879 - loss: 0.0018 - val_accuracy: 0.9770 - val_loss: 0.0025\n",
       "Epoch 121/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0026 - accuracy: 0.9873 - val_loss: 0.0031 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9855 - loss: 0.0022 - val_accuracy: 0.9655 - val_loss: 0.0035\n",
       "Epoch 122/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0025 - accuracy: 0.9850 - val_loss: 0.0024 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9925 - loss: 0.0020 - val_accuracy: 0.9770 - val_loss: 0.0016\n",
       "Epoch 123/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0032 - accuracy: 0.9822 - val_loss: 0.0020 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9776 - loss: 0.0019 - val_accuracy: 1.0000 - val_loss: 0.0020\n",
       "Epoch 124/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9845 - val_loss: 0.0024 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9884 - loss: 0.0020 - val_accuracy: 0.9655 - val_loss: 9.9661e-04\n",
       "Epoch 125/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0022 - accuracy: 0.9856 - val_loss: 0.0028 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9902 - loss: 0.0020 - val_accuracy: 1.0000 - val_loss: 0.0018\n",
       "Epoch 126/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0025 - accuracy: 0.9873 - val_loss: 0.0021 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9830 - loss: 0.0018 - val_accuracy: 0.9770 - val_loss: 0.0021\n",
       "Epoch 127/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0030 - accuracy: 0.9833 - val_loss: 0.0022 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9888 - loss: 0.0019 - val_accuracy: 0.9885 - val_loss: 0.0022\n",
       "Epoch 128/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0029 - accuracy: 0.9862 - val_loss: 0.0021 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9875 - loss: 0.0017 - val_accuracy: 1.0000 - val_loss: 0.0016\n",
       "Epoch 129/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0030 - accuracy: 0.9839 - val_loss: 0.0017 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9918 - loss: 0.0029 - val_accuracy: 1.0000 - val_loss: 0.0016\n",
       "Epoch 130/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0023 - accuracy: 0.9822 - val_loss: 0.0025 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9870 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 0.0019\n",
       "Epoch 131/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0025 - accuracy: 0.9839 - val_loss: 0.0023 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9895 - loss: 0.0019 - val_accuracy: 0.9885 - val_loss: 0.0015\n",
       "Epoch 132/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9833 - val_loss: 0.0018 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9860 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 0.0022\n",
       "Epoch 133/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0029 - accuracy: 0.9873 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9790 - loss: 0.0020 - val_accuracy: 1.0000 - val_loss: 0.0015\n",
       "Epoch 134/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9822 - val_loss: 0.0021 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9872 - loss: 0.0017 - val_accuracy: 0.9770 - val_loss: 0.0018\n",
       "Epoch 135/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0022 - accuracy: 0.9816 - val_loss: 0.0018 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9819 - loss: 0.0016 - val_accuracy: 0.9885 - val_loss: 0.0018\n",
       "Epoch 136/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9850 - val_loss: 0.0021 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9867 - loss: 0.0017 - val_accuracy: 0.9770 - val_loss: 0.0022\n",
       "Epoch 137/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9850 - val_loss: 0.0016 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9908 - loss: 0.0017 - val_accuracy: 0.9770 - val_loss: 0.0014\n",
       "Epoch 138/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9810 - val_loss: 0.0020 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9902 - loss: 0.0023 - val_accuracy: 0.9885 - val_loss: 0.0017\n",
       "Epoch 139/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9862 - val_loss: 0.0016 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9871 - loss: 0.0016 - val_accuracy: 1.0000 - val_loss: 0.0017\n",
       "Epoch 140/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0028 - accuracy: 0.9845 - val_loss: 0.0016 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9910 - loss: 0.0018 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 141/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9816 - val_loss: 0.0019 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9841 - loss: 0.0016 - val_accuracy: 0.9885 - val_loss: 0.0015\n",
       "Epoch 142/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0023 - accuracy: 0.9827 - val_loss: 0.0032 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9824 - loss: 0.0015 - val_accuracy: 1.0000 - val_loss: 0.0029\n",
       "Epoch 143/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0027 - accuracy: 0.9850 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9861 - loss: 0.0017 - val_accuracy: 1.0000 - val_loss: 0.0015\n",
       "Epoch 144/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0025 - accuracy: 0.9868 - val_loss: 0.0024 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9805 - loss: 0.0016 - val_accuracy: 0.9885 - val_loss: 0.0019\n",
       "Epoch 145/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9879 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9825 - loss: 0.0015 - val_accuracy: 0.9885 - val_loss: 0.0018\n",
       "Epoch 146/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9845 - val_loss: 0.0019 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9893 - loss: 0.0017 - val_accuracy: 1.0000 - val_loss: 0.0026\n",
       "Epoch 147/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9879 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9849 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 0.0014\n",
       "Epoch 148/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0022 - accuracy: 0.9914 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9902 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 0.0013\n",
       "Epoch 149/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0028 - accuracy: 0.9839 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9890 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 0.0013\n",
       "Epoch 150/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0020 - accuracy: 0.9879 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - accuracy: 0.9821 - loss: 0.0018 - val_accuracy: 0.9885 - val_loss: 0.0014\n",
       "Epoch 151/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0025 - accuracy: 0.9839 - val_loss: 0.0018 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9876 - loss: 0.0019 - val_accuracy: 0.9770 - val_loss: 0.0013\n",
       "Epoch 152/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0019 - accuracy: 0.9868 - val_loss: 0.0017 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9923 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 0.0011\n",
       "Epoch 153/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9850 - val_loss: 0.0028 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9900 - loss: 0.0014 - val_accuracy: 0.9655 - val_loss: 0.0015\n",
       "Epoch 154/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0023 - accuracy: 0.9908 - val_loss: 0.0016 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9861 - loss: 0.0015 - val_accuracy: 1.0000 - val_loss: 0.0013\n",
       "Epoch 155/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0030 - accuracy: 0.9833 - val_loss: 0.0027 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9857 - loss: 0.0020 - val_accuracy: 0.9885 - val_loss: 0.0017\n",
       "Epoch 156/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9862 - val_loss: 0.0022 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9884 - loss: 0.0014 - val_accuracy: 1.0000 - val_loss: 0.0016\n",
       "Epoch 157/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0020 - accuracy: 0.9850 - val_loss: 0.0022 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9820 - loss: 0.0017 - val_accuracy: 1.0000 - val_loss: 0.0015\n",
       "Epoch 158/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0025 - accuracy: 0.9862 - val_loss: 0.0037 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9871 - loss: 0.0015 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 159/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0022 - accuracy: 0.9868 - val_loss: 0.0019 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9838 - loss: 0.0014 - val_accuracy: 0.9885 - val_loss: 0.0016\n",
       "Epoch 160/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0022 - accuracy: 0.9839 - val_loss: 0.0019 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9826 - loss: 0.0016 - val_accuracy: 0.9655 - val_loss: 0.0015\n",
       "Epoch 161/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0019 - accuracy: 0.9804 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9872 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 0.0014\n",
       "Epoch 162/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0022 - accuracy: 0.9879 - val_loss: 0.0047 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9863 - loss: 0.0020 - val_accuracy: 0.9885 - val_loss: 0.0013\n",
       "Epoch 163/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0024 - accuracy: 0.9845 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9889 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 8.8989e-04\n",
       "Epoch 164/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9908 - val_loss: 0.0023 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9886 - loss: 0.0014 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 165/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0026 - accuracy: 0.9868 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9888 - loss: 0.0013 - val_accuracy: 0.9770 - val_loss: 0.0012\n",
       "Epoch 166/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0020 - accuracy: 0.9873 - val_loss: 0.0055 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9886 - loss: 0.0014 - val_accuracy: 1.0000 - val_loss: 9.9103e-04\n",
       "Epoch 167/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0019 - accuracy: 0.9856 - val_loss: 0.0038 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9868 - loss: 0.0014 - val_accuracy: 1.0000 - val_loss: 0.0015\n",
       "Epoch 168/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0026 - accuracy: 0.9885 - val_loss: 0.0014 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9922 - loss: 0.0012 - val_accuracy: 1.0000 - val_loss: 0.0016\n",
       "Epoch 169/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9868 - val_loss: 0.0025 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9850 - loss: 0.0014 - val_accuracy: 0.9885 - val_loss: 0.0015\n",
       "Epoch 170/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0019 - accuracy: 0.9885 - val_loss: 0.0017 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9879 - loss: 0.0017 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 171/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9850 - val_loss: 0.0025 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9909 - loss: 0.0015 - val_accuracy: 0.9770 - val_loss: 0.0015\n",
       "Epoch 172/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0022 - accuracy: 0.9850 - val_loss: 0.0019 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9926 - loss: 0.0014 - val_accuracy: 1.0000 - val_loss: 0.0012\n",
       "Epoch 173/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0019 - accuracy: 0.9850 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9873 - loss: 0.0016 - val_accuracy: 0.9770 - val_loss: 0.0013\n",
       "Epoch 174/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0020 - accuracy: 0.9873 - val_loss: 0.0018 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9854 - loss: 0.0014 - val_accuracy: 0.9655 - val_loss: 0.0011\n",
       "Epoch 175/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0025 - accuracy: 0.9862 - val_loss: 0.0025 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9909 - loss: 0.0011 - val_accuracy: 0.9770 - val_loss: 0.0033\n",
       "Epoch 176/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9862 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9912 - loss: 0.0019 - val_accuracy: 1.0000 - val_loss: 0.0011\n",
       "Epoch 177/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0022 - accuracy: 0.9839 - val_loss: 0.0015 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9863 - loss: 0.0014 - val_accuracy: 1.0000 - val_loss: 0.0011\n",
       "Epoch 178/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9850 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9842 - loss: 0.0016 - val_accuracy: 0.9885 - val_loss: 0.0010\n",
       "Epoch 179/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9856 - val_loss: 0.0018 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9923 - loss: 0.0014 - val_accuracy: 0.9885 - val_loss: 0.0016\n",
       "Epoch 180/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9879 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9891 - loss: 0.0015 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 181/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9850 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9852 - loss: 0.0013 - val_accuracy: 0.9885 - val_loss: 0.0021\n",
       "Epoch 182/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9862 - val_loss: 0.0013 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9899 - loss: 0.0013 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 183/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9862 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9939 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 8.8295e-04\n",
       "Epoch 184/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0016 - accuracy: 0.9914 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9907 - loss: 0.0015 - val_accuracy: 0.9770 - val_loss: 9.6851e-04\n",
       "Epoch 185/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9839 - val_loss: 0.0019 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9873 - loss: 0.0014 - val_accuracy: 0.9770 - val_loss: 0.0019\n",
       "Epoch 186/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9833 - val_loss: 0.0020 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 8ms/step - accuracy: 0.9898 - loss: 0.0013 - val_accuracy: 0.9770 - val_loss: 0.0012\n",
       "Epoch 187/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0019 - accuracy: 0.9839 - val_loss: 0.0021 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9906 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 8.6663e-04\n",
       "Epoch 188/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9862 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9903 - loss: 0.0014 - val_accuracy: 1.0000 - val_loss: 0.0017\n",
       "Epoch 189/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0017 - accuracy: 0.9845 - val_loss: 0.0014 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9914 - loss: 0.0012 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 190/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9862 - val_loss: 0.0016 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9880 - loss: 0.0013 - val_accuracy: 0.9770 - val_loss: 0.0013\n",
       "Epoch 191/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9856 - val_loss: 0.0016 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9894 - loss: 0.0012 - val_accuracy: 1.0000 - val_loss: 0.0015\n",
       "Epoch 192/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0021 - accuracy: 0.9850 - val_loss: 0.0028 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9854 - loss: 0.0012 - val_accuracy: 1.0000 - val_loss: 0.0011\n",
       "Epoch 193/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0016 - accuracy: 0.9879 - val_loss: 0.0017 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9895 - loss: 0.0014 - val_accuracy: 0.9885 - val_loss: 0.0014\n",
       "Epoch 194/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9891 - val_loss: 0.0016 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9889 - loss: 0.0014 - val_accuracy: 1.0000 - val_loss: 9.5950e-04\n",
       "Epoch 195/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0016 - accuracy: 0.9862 - val_loss: 0.0016 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9861 - loss: 0.0011 - val_accuracy: 0.9885 - val_loss: 0.0016\n",
       "Epoch 196/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0016 - accuracy: 0.9908 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9904 - loss: 0.0011 - val_accuracy: 0.9885 - val_loss: 9.4874e-04\n",
       "Epoch 197/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9862 - val_loss: 0.0017 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9888 - loss: 0.0011 - val_accuracy: 1.0000 - val_loss: 0.0016\n",
       "Epoch 198/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9850 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9906 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 9.3728e-04\n",
       "Epoch 199/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0015 - accuracy: 0.9850 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9851 - loss: 0.0011 - val_accuracy: 0.9885 - val_loss: 8.7937e-04\n",
       "Epoch 200/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9885 - val_loss: 0.0017 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9877 - loss: 0.0013 - val_accuracy: 0.9770 - val_loss: 0.0013\n",
       "Epoch 201/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0015 - accuracy: 0.9891 - val_loss: 0.0016 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9876 - loss: 0.0014 - val_accuracy: 0.9885 - val_loss: 8.1628e-04\n",
       "Epoch 202/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0019 - accuracy: 0.9845 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9880 - loss: 9.8585e-04 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 203/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9879 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9860 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 9.0658e-04\n",
       "Epoch 204/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9839 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9917 - loss: 9.8009e-04 - val_accuracy: 1.0000 - val_loss: 0.0011\n",
       "Epoch 205/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9885 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9898 - loss: 0.0012 - val_accuracy: 0.9885 - val_loss: 7.0668e-04\n",
       "Epoch 206/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0014 - accuracy: 0.9879 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9947 - loss: 0.0011 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 207/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0015 - accuracy: 0.9896 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9932 - loss: 0.0011 - val_accuracy: 0.9770 - val_loss: 0.0012\n",
       "Epoch 208/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9902 - val_loss: 0.0015 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9892 - loss: 0.0011 - val_accuracy: 1.0000 - val_loss: 0.0013\n",
       "Epoch 209/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9873 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9940 - loss: 0.0011 - val_accuracy: 1.0000 - val_loss: 7.6506e-04\n",
       "Epoch 210/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9868 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9862 - loss: 0.0012 - val_accuracy: 1.0000 - val_loss: 7.1302e-04\n",
       "Epoch 211/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0017 - accuracy: 0.9891 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9871 - loss: 0.0011 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 212/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0015 - accuracy: 0.9850 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9900 - loss: 9.8896e-04 - val_accuracy: 0.9885 - val_loss: 8.8623e-04\n",
       "Epoch 213/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0017 - accuracy: 0.9925 - val_loss: 0.0016 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9927 - loss: 0.0011 - val_accuracy: 0.9770 - val_loss: 7.9862e-04\n",
       "Epoch 214/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0016 - accuracy: 0.9879 - val_loss: 0.0044 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9871 - loss: 0.0012 - val_accuracy: 0.9885 - val_loss: 0.0010\n",
       "Epoch 215/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0015 - accuracy: 0.9850 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9922 - loss: 0.0012 - val_accuracy: 0.9655 - val_loss: 8.0919e-04\n",
       "Epoch 216/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0018 - accuracy: 0.9891 - val_loss: 0.0039 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9928 - loss: 0.0012 - val_accuracy: 0.9770 - val_loss: 8.4679e-04\n",
       "Epoch 217/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0016 - accuracy: 0.9845 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9907 - loss: 9.5629e-04 - val_accuracy: 0.9885 - val_loss: 9.0092e-04\n",
       "Epoch 218/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0016 - accuracy: 0.9856 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9907 - loss: 0.0011 - val_accuracy: 0.9770 - val_loss: 8.6552e-04\n",
       "Epoch 219/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0015 - accuracy: 0.9856 - val_loss: 9.9744e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9927 - loss: 0.0011 - val_accuracy: 1.0000 - val_loss: 0.0013\n",
       "Epoch 220/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0015 - accuracy: 0.9891 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9930 - loss: 0.0011 - val_accuracy: 0.9770 - val_loss: 0.0012\n",
       "Epoch 221/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0015 - accuracy: 0.9868 - val_loss: 0.0018 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9873 - loss: 0.0011 - val_accuracy: 0.9885 - val_loss: 9.0425e-04\n",
       "Epoch 222/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0016 - accuracy: 0.9902 - val_loss: 0.0014 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9891 - loss: 0.0010 - val_accuracy: 0.9885 - val_loss: 9.7249e-04\n",
       "Epoch 223/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0014 - accuracy: 0.9891 - val_loss: 0.0018 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9915 - loss: 0.0011 - val_accuracy: 0.9770 - val_loss: 0.0014\n",
       "Epoch 224/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0016 - accuracy: 0.9873 - val_loss: 0.0022 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9876 - loss: 0.0010 - val_accuracy: 1.0000 - val_loss: 9.2950e-04\n",
       "Epoch 225/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0014 - accuracy: 0.9850 - val_loss: 0.0016 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9929 - loss: 0.0010 - val_accuracy: 0.9885 - val_loss: 6.2259e-04\n",
       "Epoch 226/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0016 - accuracy: 0.9891 - val_loss: 8.3345e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9877 - loss: 9.0506e-04 - val_accuracy: 0.9770 - val_loss: 7.1474e-04\n",
       "Epoch 227/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0014 - accuracy: 0.9891 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9882 - loss: 9.6452e-04 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 228/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0016 - accuracy: 0.9885 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9932 - loss: 9.6913e-04 - val_accuracy: 0.9885 - val_loss: 0.0010\n",
       "Epoch 229/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0013 - accuracy: 0.9919 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9905 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 9.8952e-04\n",
       "Epoch 230/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0014 - accuracy: 0.9919 - val_loss: 0.0013 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9924 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 0.0010\n",
       "Epoch 231/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0014 - accuracy: 0.9868 - val_loss: 0.0022 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9880 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 0.0011\n",
       "Epoch 232/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0016 - accuracy: 0.9896 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9851 - loss: 0.0011 - val_accuracy: 1.0000 - val_loss: 0.0012\n",
       "Epoch 233/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0014 - accuracy: 0.9868 - val_loss: 0.0017 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9878 - loss: 0.0010 - val_accuracy: 1.0000 - val_loss: 7.6264e-04\n",
       "Epoch 234/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0015 - accuracy: 0.9931 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9893 - loss: 0.0011 - val_accuracy: 1.0000 - val_loss: 8.8791e-04\n",
       "Epoch 235/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0016 - accuracy: 0.9873 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9942 - loss: 9.4382e-04 - val_accuracy: 1.0000 - val_loss: 6.7514e-04\n",
       "Epoch 236/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0014 - accuracy: 0.9896 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9846 - loss: 0.0013 - val_accuracy: 0.9885 - val_loss: 9.3449e-04\n",
       "Epoch 237/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0014 - accuracy: 0.9914 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9898 - loss: 9.3972e-04 - val_accuracy: 0.9655 - val_loss: 8.7290e-04\n",
       "Epoch 238/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0015 - accuracy: 0.9896 - val_loss: 9.7463e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9939 - loss: 0.0010 - val_accuracy: 1.0000 - val_loss: 9.1843e-04\n",
       "Epoch 239/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0014 - accuracy: 0.9885 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9905 - loss: 0.0010 - val_accuracy: 0.9770 - val_loss: 7.7935e-04\n",
       "Epoch 240/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0013 - accuracy: 0.9902 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9847 - loss: 9.8542e-04 - val_accuracy: 0.9770 - val_loss: 8.5203e-04\n",
       "Epoch 241/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0015 - accuracy: 0.9879 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9921 - loss: 0.0011 - val_accuracy: 0.9885 - val_loss: 7.3658e-04\n",
       "Epoch 242/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0012 - accuracy: 0.9850 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9925 - loss: 9.0024e-04 - val_accuracy: 0.9885 - val_loss: 8.2399e-04\n",
       "Epoch 243/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0015 - accuracy: 0.9879 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9936 - loss: 0.0010 - val_accuracy: 0.9885 - val_loss: 7.8918e-04\n",
       "Epoch 244/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0014 - accuracy: 0.9919 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9897 - loss: 9.1121e-04 - val_accuracy: 0.9885 - val_loss: 8.2400e-04\n",
       "Epoch 245/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0012 - accuracy: 0.9873 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9935 - loss: 9.0638e-04 - val_accuracy: 0.9885 - val_loss: 6.6980e-04\n",
       "Epoch 246/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0013 - accuracy: 0.9885 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9906 - loss: 8.7518e-04 - val_accuracy: 0.9885 - val_loss: 9.5346e-04\n",
       "Epoch 247/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0015 - accuracy: 0.9868 - val_loss: 0.0014 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9910 - loss: 0.0010 - val_accuracy: 0.9885 - val_loss: 6.9845e-04\n",
       "Epoch 248/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0014 - accuracy: 0.9885 - val_loss: 9.5796e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9919 - loss: 8.7809e-04 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 249/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0013 - accuracy: 0.9896 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9933 - loss: 8.3932e-04 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 250/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0013 - accuracy: 0.9931 - val_loss: 0.0014 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9922 - loss: 9.4577e-04 - val_accuracy: 1.0000 - val_loss: 5.4011e-04\n",
       "Epoch 251/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0014 - accuracy: 0.9919 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - accuracy: 0.9939 - loss: 9.4001e-04 - val_accuracy: 1.0000 - val_loss: 7.5942e-04\n",
       "Epoch 252/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0016 - accuracy: 0.9850 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9934 - loss: 0.0010 - val_accuracy: 1.0000 - val_loss: 7.8934e-04\n",
       "Epoch 253/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0011 - accuracy: 0.9879 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9883 - loss: 8.9882e-04 - val_accuracy: 0.9770 - val_loss: 9.3218e-04\n",
       "Epoch 254/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9896 - val_loss: 0.0013 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 8ms/step - accuracy: 0.9930 - loss: 9.2573e-04 - val_accuracy: 1.0000 - val_loss: 7.3275e-04\n",
       "Epoch 255/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9891 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9877 - loss: 8.2303e-04 - val_accuracy: 0.9885 - val_loss: 5.4043e-04\n",
       "Epoch 256/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0013 - accuracy: 0.9868 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 8ms/step - accuracy: 0.9931 - loss: 9.3408e-04 - val_accuracy: 1.0000 - val_loss: 0.0014\n",
       "Epoch 257/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0013 - accuracy: 0.9879 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 9ms/step - accuracy: 0.9848 - loss: 8.8354e-04 - val_accuracy: 0.9770 - val_loss: 7.5163e-04\n",
       "Epoch 258/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0012 - accuracy: 0.9868 - val_loss: 9.1944e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9950 - loss: 8.3677e-04 - val_accuracy: 0.9885 - val_loss: 6.8823e-04\n",
       "Epoch 259/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0013 - accuracy: 0.9914 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9915 - loss: 9.0890e-04 - val_accuracy: 0.9885 - val_loss: 0.0010\n",
       "Epoch 260/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0012 - accuracy: 0.9891 - val_loss: 8.8243e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9836 - loss: 9.1826e-04 - val_accuracy: 1.0000 - val_loss: 7.1593e-04\n",
       "Epoch 261/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0013 - accuracy: 0.9925 - val_loss: 0.0012 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9911 - loss: 8.3884e-04 - val_accuracy: 1.0000 - val_loss: 0.0010\n",
       "Epoch 262/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0012 - accuracy: 0.9868 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9886 - loss: 9.0946e-04 - val_accuracy: 1.0000 - val_loss: 7.2467e-04\n",
       "Epoch 263/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0014 - accuracy: 0.9908 - val_loss: 8.7958e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9924 - loss: 8.5208e-04 - val_accuracy: 0.9885 - val_loss: 0.0011\n",
       "Epoch 264/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9919 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9948 - loss: 9.3617e-04 - val_accuracy: 0.9885 - val_loss: 8.4313e-04\n",
       "Epoch 265/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9850 - val_loss: 7.9670e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9965 - loss: 8.8620e-04 - val_accuracy: 1.0000 - val_loss: 0.0012\n",
       "Epoch 266/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9891 - val_loss: 9.7937e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9890 - loss: 9.6209e-04 - val_accuracy: 1.0000 - val_loss: 5.9627e-04\n",
       "Epoch 267/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9885 - val_loss: 7.9104e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9927 - loss: 8.5597e-04 - val_accuracy: 0.9885 - val_loss: 5.4875e-04\n",
       "Epoch 268/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9914 - val_loss: 0.0012 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9905 - loss: 7.9574e-04 - val_accuracy: 0.9770 - val_loss: 6.0788e-04\n",
       "Epoch 269/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9896 - val_loss: 9.4099e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9913 - loss: 8.3122e-04 - val_accuracy: 0.9770 - val_loss: 9.6944e-04\n",
       "Epoch 270/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9914 - val_loss: 9.5015e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9884 - loss: 8.6850e-04 - val_accuracy: 1.0000 - val_loss: 7.4577e-04\n",
       "Epoch 271/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9885 - val_loss: 8.9376e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9959 - loss: 8.4303e-04 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 272/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9868 - val_loss: 9.1806e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9886 - loss: 9.1454e-04 - val_accuracy: 1.0000 - val_loss: 4.3174e-04\n",
       "Epoch 273/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9885 - val_loss: 0.0011 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9922 - loss: 7.5023e-04 - val_accuracy: 0.9885 - val_loss: 5.8617e-04\n",
       "Epoch 274/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9862 - val_loss: 0.0010 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9891 - loss: 7.6872e-04 - val_accuracy: 1.0000 - val_loss: 8.0284e-04\n",
       "Epoch 275/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9902 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9816 - loss: 0.0013 - val_accuracy: 1.0000 - val_loss: 9.4248e-04\n",
       "Epoch 276/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9879 - val_loss: 0.0014 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9908 - loss: 8.1808e-04 - val_accuracy: 0.9885 - val_loss: 5.6248e-04\n",
       "Epoch 277/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9902 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9941 - loss: 8.1954e-04 - val_accuracy: 0.9885 - val_loss: 6.9449e-04\n",
       "Epoch 278/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0013 - accuracy: 0.9908 - val_loss: 0.0012 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9938 - loss: 8.2561e-04 - val_accuracy: 0.9885 - val_loss: 7.7510e-04\n",
       "Epoch 279/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0011 - accuracy: 0.9891 - val_loss: 9.0459e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9882 - loss: 8.9868e-04 - val_accuracy: 1.0000 - val_loss: 7.7983e-04\n",
       "Epoch 280/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0013 - accuracy: 0.9891 - val_loss: 0.0015 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9896 - loss: 9.1424e-04 - val_accuracy: 1.0000 - val_loss: 5.1634e-04\n",
       "Epoch 281/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0012 - accuracy: 0.9908 - val_loss: 0.0013 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9872 - loss: 7.8297e-04 - val_accuracy: 0.9655 - val_loss: 5.5173e-04\n",
       "Epoch 282/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0011 - accuracy: 0.9873 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9918 - loss: 7.7699e-04 - val_accuracy: 0.9885 - val_loss: 9.1789e-04\n",
       "Epoch 283/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0011 - accuracy: 0.9896 - val_loss: 7.9231e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9933 - loss: 7.7968e-04 - val_accuracy: 0.9885 - val_loss: 6.8660e-04\n",
       "Epoch 284/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0011 - accuracy: 0.9908 - val_loss: 0.0014 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9930 - loss: 7.5931e-04 - val_accuracy: 1.0000 - val_loss: 6.3248e-04\n",
       "Epoch 285/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0012 - accuracy: 0.9919 - val_loss: 0.0016 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9891 - loss: 9.0076e-04 - val_accuracy: 0.9770 - val_loss: 9.2022e-04\n",
       "Epoch 286/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0010 - accuracy: 0.9902 - val_loss: 6.9346e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9902 - loss: 7.9744e-04 - val_accuracy: 1.0000 - val_loss: 5.1955e-04\n",
       "Epoch 287/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0012 - accuracy: 0.9885 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9965 - loss: 7.2101e-04 - val_accuracy: 0.9885 - val_loss: 5.8109e-04\n",
       "Epoch 288/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0012 - accuracy: 0.9896 - val_loss: 7.9960e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9936 - loss: 9.3248e-04 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 289/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0013 - accuracy: 0.9885 - val_loss: 9.5250e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9888 - loss: 7.8337e-04 - val_accuracy: 1.0000 - val_loss: 0.0012\n",
       "Epoch 290/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0011 - accuracy: 0.9879 - val_loss: 7.1742e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9948 - loss: 8.3957e-04 - val_accuracy: 0.9885 - val_loss: 7.6250e-04\n",
       "Epoch 291/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0012 - accuracy: 0.9925 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9987 - loss: 7.6988e-04 - val_accuracy: 0.9885 - val_loss: 6.2819e-04\n",
       "Epoch 292/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9919 - val_loss: 8.2050e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9871 - loss: 7.9584e-04 - val_accuracy: 1.0000 - val_loss: 3.2492e-04\n",
       "Epoch 293/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0011 - accuracy: 0.9868 - val_loss: 0.0012 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9938 - loss: 6.8409e-04 - val_accuracy: 1.0000 - val_loss: 9.0155e-04\n",
       "Epoch 294/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0011 - accuracy: 0.9862 - val_loss: 0.0015 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9915 - loss: 7.4125e-04 - val_accuracy: 1.0000 - val_loss: 6.9889e-04\n",
       "Epoch 295/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0011 - accuracy: 0.9868 - val_loss: 8.3175e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9927 - loss: 8.1052e-04 - val_accuracy: 1.0000 - val_loss: 5.6266e-04\n",
       "Epoch 296/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0012 - accuracy: 0.9902 - val_loss: 9.2405e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9951 - loss: 0.0010 - val_accuracy: 0.9770 - val_loss: 7.1752e-04\n",
       "Epoch 297/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0010 - accuracy: 0.9902 - val_loss: 9.6304e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9923 - loss: 7.2678e-04 - val_accuracy: 0.9885 - val_loss: 6.1477e-04\n",
       "Epoch 298/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9873 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9921 - loss: 6.8445e-04 - val_accuracy: 0.9885 - val_loss: 4.8350e-04\n",
       "Epoch 299/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0013 - accuracy: 0.9879 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9922 - loss: 7.8185e-04 - val_accuracy: 1.0000 - val_loss: 4.8342e-04\n",
       "Epoch 300/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0010 - accuracy: 0.9908 - val_loss: 8.7325e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9890 - loss: 7.5693e-04 - val_accuracy: 1.0000 - val_loss: 6.1901e-04\n",
       "Epoch 301/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9914 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9969 - loss: 6.8541e-04 - val_accuracy: 0.9885 - val_loss: 6.1948e-04\n",
       "Epoch 302/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0010 - accuracy: 0.9925 - val_loss: 0.0012 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9933 - loss: 6.8791e-04 - val_accuracy: 0.9885 - val_loss: 6.7574e-04\n",
       "Epoch 303/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 9.9646e-04 - accuracy: 0.9908 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9938 - loss: 6.5692e-04 - val_accuracy: 0.9885 - val_loss: 4.6391e-04\n",
       "Epoch 304/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 0.0010 - accuracy: 0.9908 - val_loss: 8.6022e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9908 - loss: 8.2576e-04 - val_accuracy: 0.9770 - val_loss: 7.3254e-04\n",
       "Epoch 305/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0011 - accuracy: 0.9908 - val_loss: 8.3776e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9948 - loss: 7.2332e-04 - val_accuracy: 1.0000 - val_loss: 9.0370e-04\n",
       "Epoch 306/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0011 - accuracy: 0.9896 - val_loss: 0.0011 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9939 - loss: 7.4702e-04 - val_accuracy: 0.9655 - val_loss: 6.9995e-04\n",
       "Epoch 307/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.6682e-04 - accuracy: 0.9902 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9900 - loss: 8.2767e-04 - val_accuracy: 0.9885 - val_loss: 5.2700e-04\n",
       "Epoch 308/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.5565e-04 - accuracy: 0.9902 - val_loss: 9.3929e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9937 - loss: 7.8130e-04 - val_accuracy: 0.9885 - val_loss: 5.6042e-04\n",
       "Epoch 309/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0011 - accuracy: 0.9908 - val_loss: 9.3008e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9913 - loss: 7.2094e-04 - val_accuracy: 0.9770 - val_loss: 7.0822e-04\n",
       "Epoch 310/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.1611e-04 - accuracy: 0.9925 - val_loss: 6.8073e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9917 - loss: 8.2865e-04 - val_accuracy: 1.0000 - val_loss: 5.1709e-04\n",
       "Epoch 311/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.3053e-04 - accuracy: 0.9891 - val_loss: 8.1744e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9991 - loss: 6.8695e-04 - val_accuracy: 1.0000 - val_loss: 6.7282e-04\n",
       "Epoch 312/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0013 - accuracy: 0.9891 - val_loss: 8.5545e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9943 - loss: 7.6217e-04 - val_accuracy: 1.0000 - val_loss: 7.7876e-04\n",
       "Epoch 313/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0010 - accuracy: 0.9891 - val_loss: 9.1545e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9963 - loss: 6.1268e-04 - val_accuracy: 1.0000 - val_loss: 0.0010\n",
       "Epoch 314/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0011 - accuracy: 0.9896 - val_loss: 6.1105e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 7.2714e-04 - val_accuracy: 0.9770 - val_loss: 8.6811e-04\n",
       "Epoch 315/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.0581e-04 - accuracy: 0.9902 - val_loss: 0.0011 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9933 - loss: 7.4919e-04 - val_accuracy: 0.9885 - val_loss: 5.3317e-04\n",
       "Epoch 316/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0010 - accuracy: 0.9896 - val_loss: 8.9868e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9917 - loss: 7.4293e-04 - val_accuracy: 0.9885 - val_loss: 9.3760e-04\n",
       "Epoch 317/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.6268e-04 - accuracy: 0.9931 - val_loss: 9.6028e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9899 - loss: 7.3231e-04 - val_accuracy: 1.0000 - val_loss: 4.1751e-04\n",
       "Epoch 318/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.6150e-04 - accuracy: 0.9862 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9953 - loss: 7.1604e-04 - val_accuracy: 0.9770 - val_loss: 6.5562e-04\n",
       "Epoch 319/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0011 - accuracy: 0.9931 - val_loss: 7.5135e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9913 - loss: 7.0229e-04 - val_accuracy: 0.9540 - val_loss: 6.2420e-04\n",
       "Epoch 320/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.7217e-04 - accuracy: 0.9908 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9904 - loss: 8.5191e-04 - val_accuracy: 0.9770 - val_loss: 6.6063e-04\n",
       "Epoch 321/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.6782e-04 - accuracy: 0.9919 - val_loss: 0.0010 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9949 - loss: 7.4928e-04 - val_accuracy: 1.0000 - val_loss: 9.8122e-04\n",
       "Epoch 322/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 9.3147e-04 - accuracy: 0.9925 - val_loss: 7.2649e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9975 - loss: 6.6767e-04 - val_accuracy: 0.9885 - val_loss: 6.2719e-04\n",
       "Epoch 323/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.9281e-04 - accuracy: 0.9896 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9889 - loss: 6.3506e-04 - val_accuracy: 0.9885 - val_loss: 0.0012\n",
       "Epoch 324/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.8488e-04 - accuracy: 0.9942 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9949 - loss: 7.1036e-04 - val_accuracy: 0.9770 - val_loss: 6.4926e-04\n",
       "Epoch 325/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 0.0011 - accuracy: 0.9896 - val_loss: 8.5299e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9949 - loss: 6.6232e-04 - val_accuracy: 1.0000 - val_loss: 8.2866e-04\n",
       "Epoch 326/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.1013e-04 - accuracy: 0.9879 - val_loss: 0.0021 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9938 - loss: 6.8625e-04 - val_accuracy: 0.9885 - val_loss: 6.7102e-04\n",
       "Epoch 327/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.9896e-04 - accuracy: 0.9879 - val_loss: 9.4131e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9961 - loss: 6.7720e-04 - val_accuracy: 0.9885 - val_loss: 6.8776e-04\n",
       "Epoch 328/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.1978e-04 - accuracy: 0.9850 - val_loss: 8.4156e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9882 - loss: 8.1775e-04 - val_accuracy: 0.9885 - val_loss: 5.4632e-04\n",
       "Epoch 329/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0010 - accuracy: 0.9931 - val_loss: 7.8394e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9923 - loss: 5.9365e-04 - val_accuracy: 0.9885 - val_loss: 4.6942e-04\n",
       "Epoch 330/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 8.9950e-04 - accuracy: 0.9914 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9904 - loss: 6.7219e-04 - val_accuracy: 1.0000 - val_loss: 7.3015e-04\n",
       "Epoch 331/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 9.5455e-04 - accuracy: 0.9902 - val_loss: 6.9671e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9945 - loss: 7.6455e-04 - val_accuracy: 0.9885 - val_loss: 5.2580e-04\n",
       "Epoch 332/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 8.7429e-04 - accuracy: 0.9937 - val_loss: 7.1404e-04 - val_accuracy: 1.0000\n",
-      "Epoch 333/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.5041e-04 - accuracy: 0.9937 - val_loss: 9.1251e-04 - val_accuracy: 1.0000\n",
-      "Epoch 334/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.2086e-04 - accuracy: 0.9902 - val_loss: 8.1689e-04 - val_accuracy: 1.0000\n",
-      "Epoch 335/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 9.5846e-04 - accuracy: 0.9914 - val_loss: 6.6067e-04 - val_accuracy: 1.0000\n",
-      "Epoch 336/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.0016e-04 - accuracy: 0.9902 - val_loss: 7.7804e-04 - val_accuracy: 1.0000\n",
-      "Epoch 337/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0011 - accuracy: 0.9914 - val_loss: 0.0010 - val_accuracy: 0.9885\n",
-      "Epoch 338/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 9.0289e-04 - accuracy: 0.9914 - val_loss: 7.2058e-04 - val_accuracy: 1.0000\n",
-      "Epoch 339/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.2461e-04 - accuracy: 0.9914 - val_loss: 6.7051e-04 - val_accuracy: 1.0000\n",
-      "Epoch 340/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.4193e-04 - accuracy: 0.9885 - val_loss: 8.8954e-04 - val_accuracy: 0.9885\n",
-      "Epoch 341/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 9.6189e-04 - accuracy: 0.9908 - val_loss: 9.0020e-04 - val_accuracy: 0.9885\n",
-      "Epoch 342/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 9.1956e-04 - accuracy: 0.9908 - val_loss: 0.0013 - val_accuracy: 1.0000\n",
-      "Epoch 343/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.9317e-04 - accuracy: 0.9919 - val_loss: 0.0010 - val_accuracy: 1.0000\n",
-      "Epoch 344/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0010 - accuracy: 0.9937 - val_loss: 6.7779e-04 - val_accuracy: 1.0000\n",
-      "Epoch 345/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.0708e-04 - accuracy: 0.9942 - val_loss: 7.5670e-04 - val_accuracy: 1.0000\n",
-      "Epoch 346/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.7028e-04 - accuracy: 0.9937 - val_loss: 0.0011 - val_accuracy: 0.9885\n",
-      "Epoch 347/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.6875e-04 - accuracy: 0.9931 - val_loss: 8.8837e-04 - val_accuracy: 1.0000\n",
-      "Epoch 348/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.3576e-04 - accuracy: 0.9948 - val_loss: 7.3743e-04 - val_accuracy: 0.9885\n",
-      "Epoch 349/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 8.2324e-04 - accuracy: 0.9914 - val_loss: 0.0012 - val_accuracy: 1.0000\n",
-      "Epoch 350/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.8852e-04 - accuracy: 0.9948 - val_loss: 0.0024 - val_accuracy: 1.0000\n",
-      "Epoch 351/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.2894e-04 - accuracy: 0.9908 - val_loss: 8.8457e-04 - val_accuracy: 1.0000\n",
-      "Epoch 352/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 8.0598e-04 - accuracy: 0.9948 - val_loss: 7.6942e-04 - val_accuracy: 1.0000\n",
-      "Epoch 353/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.2148e-04 - accuracy: 0.9925 - val_loss: 7.8839e-04 - val_accuracy: 1.0000\n",
-      "Epoch 354/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 8.8163e-04 - accuracy: 0.9891 - val_loss: 5.5069e-04 - val_accuracy: 1.0000\n",
-      "Epoch 355/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.9497e-04 - accuracy: 0.9902 - val_loss: 6.6175e-04 - val_accuracy: 1.0000\n",
-      "Epoch 356/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.8597e-04 - accuracy: 0.9925 - val_loss: 7.9081e-04 - val_accuracy: 1.0000\n",
-      "Epoch 357/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.8847e-04 - accuracy: 0.9925 - val_loss: 9.3189e-04 - val_accuracy: 1.0000\n",
-      "Epoch 358/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.1456e-04 - accuracy: 0.9902 - val_loss: 7.0651e-04 - val_accuracy: 1.0000\n",
-      "Epoch 359/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.6580e-04 - accuracy: 0.9937 - val_loss: 9.3054e-04 - val_accuracy: 1.0000\n",
-      "Epoch 360/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.8404e-04 - accuracy: 0.9937 - val_loss: 5.9532e-04 - val_accuracy: 1.0000\n",
-      "Epoch 361/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.5355e-04 - accuracy: 0.9925 - val_loss: 5.9856e-04 - val_accuracy: 1.0000\n",
-      "Epoch 362/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.9293e-04 - accuracy: 0.9948 - val_loss: 8.5525e-04 - val_accuracy: 1.0000\n",
-      "Epoch 363/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.1656e-04 - accuracy: 0.9937 - val_loss: 7.9952e-04 - val_accuracy: 1.0000\n",
-      "Epoch 364/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.3679e-04 - accuracy: 0.9902 - val_loss: 8.0514e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9945 - loss: 8.2940e-04 - val_accuracy: 1.0000 - val_loss: 4.9276e-04\n",
       "Epoch 365/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 8.5628e-04 - accuracy: 0.9896 - val_loss: 7.4580e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9930 - loss: 5.5816e-04 - val_accuracy: 1.0000 - val_loss: 4.8171e-04\n",
       "Epoch 366/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 9.3479e-04 - accuracy: 0.9919 - val_loss: 9.2393e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9957 - loss: 5.7805e-04 - val_accuracy: 1.0000 - val_loss: 6.9567e-04\n",
       "Epoch 367/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.6688e-04 - accuracy: 0.9862 - val_loss: 8.1818e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9969 - loss: 5.9225e-04 - val_accuracy: 0.9885 - val_loss: 4.5568e-04\n",
       "Epoch 368/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.5114e-04 - accuracy: 0.9931 - val_loss: 5.4912e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9931 - loss: 5.8624e-04 - val_accuracy: 1.0000 - val_loss: 5.9691e-04\n",
       "Epoch 369/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.5920e-04 - accuracy: 0.9914 - val_loss: 9.0488e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9959 - loss: 6.5817e-04 - val_accuracy: 0.9885 - val_loss: 8.8879e-04\n",
       "Epoch 370/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.0278e-04 - accuracy: 0.9942 - val_loss: 5.9102e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9923 - loss: 6.1130e-04 - val_accuracy: 0.9885 - val_loss: 4.6951e-04\n",
       "Epoch 371/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.2191e-04 - accuracy: 0.9908 - val_loss: 7.3850e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9928 - loss: 5.6217e-04 - val_accuracy: 1.0000 - val_loss: 4.6193e-04\n",
       "Epoch 372/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.2228e-04 - accuracy: 0.9942 - val_loss: 9.9475e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9938 - loss: 5.5977e-04 - val_accuracy: 0.9885 - val_loss: 4.4958e-04\n",
       "Epoch 373/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.9370e-04 - accuracy: 0.9919 - val_loss: 8.6679e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - accuracy: 0.9964 - loss: 5.3400e-04 - val_accuracy: 0.9885 - val_loss: 4.8963e-04\n",
       "Epoch 374/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.3045e-04 - accuracy: 0.9937 - val_loss: 6.5134e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9937 - loss: 6.0119e-04 - val_accuracy: 0.9885 - val_loss: 6.7206e-04\n",
       "Epoch 375/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.2399e-04 - accuracy: 0.9919 - val_loss: 5.8553e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9939 - loss: 6.1397e-04 - val_accuracy: 0.9885 - val_loss: 3.3299e-04\n",
       "Epoch 376/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.4523e-04 - accuracy: 0.9908 - val_loss: 6.9765e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - accuracy: 0.9937 - loss: 5.7036e-04 - val_accuracy: 1.0000 - val_loss: 6.8941e-04\n",
       "Epoch 377/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.7606e-04 - accuracy: 0.9914 - val_loss: 6.2357e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9940 - loss: 6.1616e-04 - val_accuracy: 0.9770 - val_loss: 4.7676e-04\n",
       "Epoch 378/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.4305e-04 - accuracy: 0.9960 - val_loss: 7.2171e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9917 - loss: 5.4421e-04 - val_accuracy: 0.9885 - val_loss: 0.0010\n",
       "Epoch 379/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.0915e-04 - accuracy: 0.9902 - val_loss: 9.9088e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9919 - loss: 4.8812e-04 - val_accuracy: 0.9885 - val_loss: 9.0622e-04\n",
       "Epoch 380/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.1508e-04 - accuracy: 0.9914 - val_loss: 6.0653e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9947 - loss: 5.7811e-04 - val_accuracy: 1.0000 - val_loss: 4.0216e-04\n",
       "Epoch 381/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.5462e-04 - accuracy: 0.9948 - val_loss: 6.8237e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9963 - loss: 6.6422e-04 - val_accuracy: 0.9885 - val_loss: 4.8791e-04\n",
       "Epoch 382/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.0104e-04 - accuracy: 0.9896 - val_loss: 7.9715e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9963 - loss: 5.4983e-04 - val_accuracy: 0.9885 - val_loss: 5.7109e-04\n",
       "Epoch 383/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.1992e-04 - accuracy: 0.9896 - val_loss: 8.6033e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9927 - loss: 5.1942e-04 - val_accuracy: 1.0000 - val_loss: 5.2900e-04\n",
       "Epoch 384/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.2105e-04 - accuracy: 0.9902 - val_loss: 7.0047e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9933 - loss: 5.2452e-04 - val_accuracy: 1.0000 - val_loss: 5.8644e-04\n",
       "Epoch 385/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.8932e-04 - accuracy: 0.9914 - val_loss: 8.6154e-04 - val_accuracy: 0.9770\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9958 - loss: 5.6571e-04 - val_accuracy: 0.9885 - val_loss: 5.8445e-04\n",
       "Epoch 386/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 7.9509e-04 - accuracy: 0.9937 - val_loss: 6.1354e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - accuracy: 0.9966 - loss: 5.7404e-04 - val_accuracy: 1.0000 - val_loss: 7.0988e-04\n",
       "Epoch 387/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 7.4731e-04 - accuracy: 0.9925 - val_loss: 7.9707e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9906 - loss: 5.4666e-04 - val_accuracy: 0.9885 - val_loss: 5.0528e-04\n",
       "Epoch 388/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 0.0011 - accuracy: 0.9908 - val_loss: 5.7792e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - accuracy: 0.9949 - loss: 5.1343e-04 - val_accuracy: 0.9885 - val_loss: 5.7529e-04\n",
       "Epoch 389/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.3737e-04 - accuracy: 0.9908 - val_loss: 0.0015 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9935 - loss: 5.5160e-04 - val_accuracy: 0.9885 - val_loss: 4.8362e-04\n",
       "Epoch 390/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.7915e-04 - accuracy: 0.9948 - val_loss: 4.2181e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9941 - loss: 5.7947e-04 - val_accuracy: 1.0000 - val_loss: 4.4065e-04\n",
       "Epoch 391/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.1164e-04 - accuracy: 0.9902 - val_loss: 8.2207e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9955 - loss: 6.1712e-04 - val_accuracy: 1.0000 - val_loss: 4.5391e-04\n",
       "Epoch 392/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.6883e-04 - accuracy: 0.9925 - val_loss: 8.4792e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9935 - loss: 5.9854e-04 - val_accuracy: 0.9770 - val_loss: 7.2638e-04\n",
       "Epoch 393/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.3374e-04 - accuracy: 0.9925 - val_loss: 6.5003e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9954 - loss: 5.8589e-04 - val_accuracy: 1.0000 - val_loss: 3.1367e-04\n",
       "Epoch 394/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.5961e-04 - accuracy: 0.9948 - val_loss: 7.1761e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9941 - loss: 5.6747e-04 - val_accuracy: 1.0000 - val_loss: 7.6702e-04\n",
       "Epoch 395/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.3330e-04 - accuracy: 0.9914 - val_loss: 9.9814e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9946 - loss: 5.5753e-04 - val_accuracy: 0.9885 - val_loss: 6.4562e-04\n",
       "Epoch 396/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.1908e-04 - accuracy: 0.9896 - val_loss: 8.3644e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9973 - loss: 7.0550e-04 - val_accuracy: 1.0000 - val_loss: 5.5498e-04\n",
       "Epoch 397/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.4392e-04 - accuracy: 0.9919 - val_loss: 7.8239e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9924 - loss: 6.0812e-04 - val_accuracy: 0.9885 - val_loss: 6.0788e-04\n",
       "Epoch 398/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 8.3754e-04 - accuracy: 0.9908 - val_loss: 6.4254e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9946 - loss: 5.8843e-04 - val_accuracy: 0.9770 - val_loss: 6.0900e-04\n",
       "Epoch 399/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 7.2238e-04 - accuracy: 0.9914 - val_loss: 7.0207e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9952 - loss: 5.6460e-04 - val_accuracy: 1.0000 - val_loss: 4.5114e-04\n",
       "Epoch 400/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 7.1025e-04 - accuracy: 0.9948 - val_loss: 6.3505e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9952 - loss: 4.6401e-04 - val_accuracy: 1.0000 - val_loss: 5.3593e-04\n",
       "Epoch 401/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.6751e-04 - accuracy: 0.9925 - val_loss: 5.4698e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9938 - loss: 5.7133e-04 - val_accuracy: 0.9885 - val_loss: 5.3777e-04\n",
       "Epoch 402/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 8.5462e-04 - accuracy: 0.9902 - val_loss: 6.6675e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9953 - loss: 7.3635e-04 - val_accuracy: 1.0000 - val_loss: 6.1640e-04\n",
       "Epoch 403/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.9554e-04 - accuracy: 0.9942 - val_loss: 6.5674e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9969 - loss: 4.9946e-04 - val_accuracy: 0.9885 - val_loss: 4.9192e-04\n",
       "Epoch 404/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.5387e-04 - accuracy: 0.9937 - val_loss: 7.8408e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9923 - loss: 5.4683e-04 - val_accuracy: 1.0000 - val_loss: 7.2880e-04\n",
       "Epoch 405/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.1186e-04 - accuracy: 0.9942 - val_loss: 6.7512e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9963 - loss: 5.2266e-04 - val_accuracy: 1.0000 - val_loss: 6.7431e-04\n",
       "Epoch 406/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 9.5202e-04 - accuracy: 0.9919 - val_loss: 5.2467e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9983 - loss: 4.5345e-04 - val_accuracy: 0.9885 - val_loss: 5.3325e-04\n",
       "Epoch 407/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.1152e-04 - accuracy: 0.9902 - val_loss: 5.6531e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9954 - loss: 5.3255e-04 - val_accuracy: 1.0000 - val_loss: 4.6317e-04\n",
       "Epoch 408/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 0.0012 - accuracy: 0.9942 - val_loss: 5.0399e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9969 - loss: 5.3661e-04 - val_accuracy: 1.0000 - val_loss: 6.1219e-04\n",
       "Epoch 409/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.6853e-04 - accuracy: 0.9931 - val_loss: 6.9926e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9899 - loss: 7.1711e-04 - val_accuracy: 0.9885 - val_loss: 4.0175e-04\n",
       "Epoch 410/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 7.4865e-04 - accuracy: 0.9942 - val_loss: 5.4852e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9894 - loss: 5.6302e-04 - val_accuracy: 1.0000 - val_loss: 4.4895e-04\n",
       "Epoch 411/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 6.9324e-04 - accuracy: 0.9925 - val_loss: 5.8081e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9965 - loss: 5.5410e-04 - val_accuracy: 0.9885 - val_loss: 4.5448e-04\n",
       "Epoch 412/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 8.4322e-04 - accuracy: 0.9954 - val_loss: 7.0079e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9895 - loss: 5.2280e-04 - val_accuracy: 0.9885 - val_loss: 4.2485e-04\n",
       "Epoch 413/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.1170e-04 - accuracy: 0.9937 - val_loss: 6.7179e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9909 - loss: 5.4494e-04 - val_accuracy: 1.0000 - val_loss: 5.9643e-04\n",
       "Epoch 414/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 8.9074e-04 - accuracy: 0.9931 - val_loss: 5.3811e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9942 - loss: 5.4045e-04 - val_accuracy: 1.0000 - val_loss: 5.6575e-04\n",
       "Epoch 415/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 6.7328e-04 - accuracy: 0.9925 - val_loss: 5.4451e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9908 - loss: 5.2818e-04 - val_accuracy: 0.9885 - val_loss: 4.5062e-04\n",
       "Epoch 416/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 6.9976e-04 - accuracy: 0.9965 - val_loss: 4.2623e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9943 - loss: 4.9531e-04 - val_accuracy: 1.0000 - val_loss: 4.4839e-04\n",
       "Epoch 417/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.4591e-04 - accuracy: 0.9942 - val_loss: 6.0065e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9931 - loss: 5.7422e-04 - val_accuracy: 1.0000 - val_loss: 4.6971e-04\n",
       "Epoch 418/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.2784e-04 - accuracy: 0.9908 - val_loss: 5.7339e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9937 - loss: 5.1630e-04 - val_accuracy: 0.9770 - val_loss: 4.3097e-04\n",
       "Epoch 419/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 7.8571e-04 - accuracy: 0.9919 - val_loss: 5.9907e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9919 - loss: 5.7681e-04 - val_accuracy: 1.0000 - val_loss: 6.2080e-04\n",
       "Epoch 420/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 8.6597e-04 - accuracy: 0.9942 - val_loss: 7.1882e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9934 - loss: 6.4706e-04 - val_accuracy: 1.0000 - val_loss: 3.8380e-04\n",
       "Epoch 421/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 7.2696e-04 - accuracy: 0.9954 - val_loss: 5.7098e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9970 - loss: 5.1780e-04 - val_accuracy: 0.9770 - val_loss: 7.0860e-04\n",
       "Epoch 422/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 6.7426e-04 - accuracy: 0.9914 - val_loss: 6.5694e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9940 - loss: 4.5436e-04 - val_accuracy: 1.0000 - val_loss: 4.7606e-04\n",
       "Epoch 423/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.8568e-04 - accuracy: 0.9908 - val_loss: 7.5126e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9942 - loss: 5.3271e-04 - val_accuracy: 1.0000 - val_loss: 4.6816e-04\n",
       "Epoch 424/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.9034e-04 - accuracy: 0.9942 - val_loss: 4.3588e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9931 - loss: 4.8219e-04 - val_accuracy: 1.0000 - val_loss: 3.8421e-04\n",
       "Epoch 425/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.6755e-04 - accuracy: 0.9919 - val_loss: 5.7710e-04 - val_accuracy: 1.0000\n",
-      "Epoch 426/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.8085e-04 - accuracy: 0.9919 - val_loss: 5.8107e-04 - val_accuracy: 1.0000\n",
-      "Epoch 427/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.6613e-04 - accuracy: 0.9931 - val_loss: 5.5483e-04 - val_accuracy: 1.0000\n",
-      "Epoch 428/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.9430e-04 - accuracy: 0.9914 - val_loss: 7.6562e-04 - val_accuracy: 1.0000\n",
-      "Epoch 429/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.5891e-04 - accuracy: 0.9908 - val_loss: 4.9008e-04 - val_accuracy: 1.0000\n",
-      "Epoch 430/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.2832e-04 - accuracy: 0.9908 - val_loss: 6.4095e-04 - val_accuracy: 1.0000\n",
-      "Epoch 431/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.9826e-04 - accuracy: 0.9948 - val_loss: 7.4883e-04 - val_accuracy: 1.0000\n",
-      "Epoch 432/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.5117e-04 - accuracy: 0.9948 - val_loss: 6.3110e-04 - val_accuracy: 1.0000\n",
-      "Epoch 433/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 6.8329e-04 - accuracy: 0.9896 - val_loss: 4.6095e-04 - val_accuracy: 1.0000\n",
-      "Epoch 434/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.2116e-04 - accuracy: 0.9902 - val_loss: 7.8973e-04 - val_accuracy: 1.0000\n",
-      "Epoch 435/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.5039e-04 - accuracy: 0.9948 - val_loss: 0.0011 - val_accuracy: 1.0000\n",
-      "Epoch 436/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.6181e-04 - accuracy: 0.9931 - val_loss: 7.0813e-04 - val_accuracy: 1.0000\n",
-      "Epoch 437/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.8155e-04 - accuracy: 0.9919 - val_loss: 5.7832e-04 - val_accuracy: 1.0000\n",
-      "Epoch 438/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.3345e-04 - accuracy: 0.9931 - val_loss: 7.5519e-04 - val_accuracy: 1.0000\n",
-      "Epoch 439/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4535e-04 - accuracy: 0.9942 - val_loss: 4.7140e-04 - val_accuracy: 1.0000\n",
-      "Epoch 440/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4785e-04 - accuracy: 0.9948 - val_loss: 4.6636e-04 - val_accuracy: 1.0000\n",
-      "Epoch 441/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.6416e-04 - accuracy: 0.9942 - val_loss: 7.4796e-04 - val_accuracy: 1.0000\n",
-      "Epoch 442/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.7270e-04 - accuracy: 0.9902 - val_loss: 6.5686e-04 - val_accuracy: 1.0000\n",
-      "Epoch 443/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.6968e-04 - accuracy: 0.9931 - val_loss: 7.7755e-04 - val_accuracy: 1.0000\n",
-      "Epoch 444/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.3466e-04 - accuracy: 0.9925 - val_loss: 5.4602e-04 - val_accuracy: 1.0000\n",
-      "Epoch 445/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 6.9028e-04 - accuracy: 0.9914 - val_loss: 5.2125e-04 - val_accuracy: 1.0000\n",
-      "Epoch 446/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.9747e-04 - accuracy: 0.9908 - val_loss: 4.5015e-04 - val_accuracy: 1.0000\n",
-      "Epoch 447/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.0155e-04 - accuracy: 0.9925 - val_loss: 8.0774e-04 - val_accuracy: 1.0000\n",
-      "Epoch 448/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.4356e-04 - accuracy: 0.9931 - val_loss: 4.3804e-04 - val_accuracy: 1.0000\n",
-      "Epoch 449/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.3899e-04 - accuracy: 0.9919 - val_loss: 5.7800e-04 - val_accuracy: 1.0000\n",
-      "Epoch 450/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.2496e-04 - accuracy: 0.9937 - val_loss: 8.3923e-04 - val_accuracy: 1.0000\n",
-      "Epoch 451/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.7241e-04 - accuracy: 0.9931 - val_loss: 6.9076e-04 - val_accuracy: 1.0000\n",
-      "Epoch 452/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.1661e-04 - accuracy: 0.9954 - val_loss: 4.3912e-04 - val_accuracy: 1.0000\n",
-      "Epoch 453/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.6805e-04 - accuracy: 0.9902 - val_loss: 6.3061e-04 - val_accuracy: 1.0000\n",
-      "Epoch 454/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2092e-04 - accuracy: 0.9937 - val_loss: 4.5542e-04 - val_accuracy: 1.0000\n",
-      "Epoch 455/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0068e-04 - accuracy: 0.9931 - val_loss: 4.9127e-04 - val_accuracy: 1.0000\n",
-      "Epoch 456/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.1622e-04 - accuracy: 0.9914 - val_loss: 6.4791e-04 - val_accuracy: 1.0000\n",
-      "Epoch 457/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.3487e-04 - accuracy: 0.9942 - val_loss: 4.9459e-04 - val_accuracy: 1.0000\n",
-      "Epoch 458/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5803e-04 - accuracy: 0.9942 - val_loss: 9.2816e-04 - val_accuracy: 1.0000\n",
-      "Epoch 459/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2458e-04 - accuracy: 0.9896 - val_loss: 4.8202e-04 - val_accuracy: 1.0000\n",
-      "Epoch 460/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4869e-04 - accuracy: 0.9914 - val_loss: 4.8873e-04 - val_accuracy: 1.0000\n",
-      "Epoch 461/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0251e-04 - accuracy: 0.9942 - val_loss: 5.2168e-04 - val_accuracy: 1.0000\n",
-      "Epoch 462/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4203e-04 - accuracy: 0.9937 - val_loss: 4.2926e-04 - val_accuracy: 1.0000\n",
-      "Epoch 463/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.7110e-04 - accuracy: 0.9919 - val_loss: 4.1157e-04 - val_accuracy: 1.0000\n",
-      "Epoch 464/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.5009e-04 - accuracy: 0.9954 - val_loss: 6.8443e-04 - val_accuracy: 1.0000\n",
-      "Epoch 465/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4688e-04 - accuracy: 0.9937 - val_loss: 6.6309e-04 - val_accuracy: 1.0000\n",
-      "Epoch 466/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0368e-04 - accuracy: 0.9948 - val_loss: 8.2036e-04 - val_accuracy: 1.0000\n",
-      "Epoch 467/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.6294e-04 - accuracy: 0.9908 - val_loss: 4.3587e-04 - val_accuracy: 1.0000\n",
-      "Epoch 468/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.7965e-04 - accuracy: 0.9937 - val_loss: 6.0045e-04 - val_accuracy: 1.0000\n",
-      "Epoch 469/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.3804e-04 - accuracy: 0.9919 - val_loss: 4.8715e-04 - val_accuracy: 1.0000\n",
-      "Epoch 470/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0555e-04 - accuracy: 0.9971 - val_loss: 5.5506e-04 - val_accuracy: 1.0000\n",
-      "Epoch 471/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.8128e-04 - accuracy: 0.9960 - val_loss: 4.9834e-04 - val_accuracy: 1.0000\n",
-      "Epoch 472/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4240e-04 - accuracy: 0.9914 - val_loss: 5.5821e-04 - val_accuracy: 1.0000\n",
-      "Epoch 473/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4672e-04 - accuracy: 0.9937 - val_loss: 0.0014 - val_accuracy: 1.0000\n",
-      "Epoch 474/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0985e-04 - accuracy: 0.9908 - val_loss: 3.9437e-04 - val_accuracy: 1.0000\n",
-      "Epoch 475/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4748e-04 - accuracy: 0.9919 - val_loss: 7.2553e-04 - val_accuracy: 1.0000\n",
-      "Epoch 476/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2077e-04 - accuracy: 0.9948 - val_loss: 5.0380e-04 - val_accuracy: 1.0000\n",
-      "Epoch 477/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0463e-04 - accuracy: 0.9937 - val_loss: 6.0317e-04 - val_accuracy: 1.0000\n",
-      "Epoch 478/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2868e-04 - accuracy: 0.9937 - val_loss: 5.5973e-04 - val_accuracy: 1.0000\n",
-      "Epoch 479/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2317e-04 - accuracy: 0.9937 - val_loss: 6.6162e-04 - val_accuracy: 1.0000\n",
-      "Epoch 480/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 6.8803e-04 - accuracy: 0.9937 - val_loss: 4.4887e-04 - val_accuracy: 1.0000\n",
-      "Epoch 481/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.5623e-04 - accuracy: 0.9948 - val_loss: 6.0076e-04 - val_accuracy: 1.0000\n",
-      "Epoch 482/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9007e-04 - accuracy: 0.9948 - val_loss: 3.2621e-04 - val_accuracy: 1.0000\n",
-      "Epoch 483/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2282e-04 - accuracy: 0.9942 - val_loss: 4.1529e-04 - val_accuracy: 1.0000\n",
-      "Epoch 484/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2902e-04 - accuracy: 0.9942 - val_loss: 8.1367e-04 - val_accuracy: 1.0000\n",
-      "Epoch 485/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 5.9548e-04 - accuracy: 0.9937 - val_loss: 4.7654e-04 - val_accuracy: 1.0000\n",
-      "Epoch 486/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 6.0079e-04 - accuracy: 0.9919 - val_loss: 4.9492e-04 - val_accuracy: 1.0000\n",
-      "Epoch 487/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2276e-04 - accuracy: 0.9919 - val_loss: 7.5990e-04 - val_accuracy: 1.0000\n",
-      "Epoch 488/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 6.2353e-04 - accuracy: 0.9954 - val_loss: 6.2431e-04 - val_accuracy: 1.0000\n",
-      "Epoch 489/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 5.5556e-04 - accuracy: 0.9965 - val_loss: 3.7814e-04 - val_accuracy: 1.0000\n",
-      "Epoch 490/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 6.1619e-04 - accuracy: 0.9919 - val_loss: 6.0067e-04 - val_accuracy: 1.0000\n",
-      "Epoch 491/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 5.7019e-04 - accuracy: 0.9925 - val_loss: 6.3317e-04 - val_accuracy: 1.0000\n",
-      "Epoch 492/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 5.9324e-04 - accuracy: 0.9914 - val_loss: 5.6922e-04 - val_accuracy: 1.0000\n",
-      "Epoch 493/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9894e-04 - accuracy: 0.9925 - val_loss: 5.1200e-04 - val_accuracy: 1.0000\n",
-      "Epoch 494/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.1210e-04 - accuracy: 0.9971 - val_loss: 5.4156e-04 - val_accuracy: 1.0000\n",
-      "Epoch 495/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 5.7179e-04 - accuracy: 0.9954 - val_loss: 7.0798e-04 - val_accuracy: 1.0000\n",
-      "Epoch 496/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 5.5456e-04 - accuracy: 0.9914 - val_loss: 4.8482e-04 - val_accuracy: 1.0000\n",
-      "Epoch 497/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 6.1764e-04 - accuracy: 0.9919 - val_loss: 5.7606e-04 - val_accuracy: 1.0000\n",
-      "Epoch 498/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 6.5475e-04 - accuracy: 0.9965 - val_loss: 5.0998e-04 - val_accuracy: 1.0000\n",
-      "Epoch 499/1000\n",
-      "218/218 [==============================] - 2s 9ms/step - loss: 5.5514e-04 - accuracy: 0.9919 - val_loss: 5.0402e-04 - val_accuracy: 1.0000\n",
-      "Epoch 500/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 5.4832e-04 - accuracy: 0.9942 - val_loss: 4.0713e-04 - val_accuracy: 1.0000\n",
-      "Epoch 501/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.3574e-04 - accuracy: 0.9948 - val_loss: 4.3171e-04 - val_accuracy: 1.0000\n",
-      "Epoch 502/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.8084e-04 - accuracy: 0.9937 - val_loss: 4.7084e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9958 - loss: 4.5994e-04 - val_accuracy: 0.9885 - val_loss: 5.1815e-04\n",
       "Epoch 503/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.7698e-04 - accuracy: 0.9948 - val_loss: 5.0148e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9969 - loss: 4.7451e-04 - val_accuracy: 1.0000 - val_loss: 3.9825e-04\n",
       "Epoch 504/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4958e-04 - accuracy: 0.9948 - val_loss: 4.9392e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9981 - loss: 4.0533e-04 - val_accuracy: 1.0000 - val_loss: 3.3114e-04\n",
       "Epoch 505/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0979e-04 - accuracy: 0.9937 - val_loss: 4.3205e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9951 - loss: 4.1795e-04 - val_accuracy: 0.9885 - val_loss: 3.0135e-04\n",
       "Epoch 506/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.7323e-04 - accuracy: 0.9908 - val_loss: 4.3737e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9965 - loss: 4.1241e-04 - val_accuracy: 0.9770 - val_loss: 4.9259e-04\n",
       "Epoch 507/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.7360e-04 - accuracy: 0.9965 - val_loss: 3.9901e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9921 - loss: 3.7994e-04 - val_accuracy: 1.0000 - val_loss: 2.4972e-04\n",
       "Epoch 508/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5322e-04 - accuracy: 0.9971 - val_loss: 6.6977e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9936 - loss: 3.8168e-04 - val_accuracy: 0.9770 - val_loss: 4.4399e-04\n",
       "Epoch 509/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3969e-04 - accuracy: 0.9902 - val_loss: 3.6894e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9980 - loss: 4.1268e-04 - val_accuracy: 0.9885 - val_loss: 4.4797e-04\n",
       "Epoch 510/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9368e-04 - accuracy: 0.9942 - val_loss: 6.2293e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9950 - loss: 4.2264e-04 - val_accuracy: 1.0000 - val_loss: 4.1988e-04\n",
       "Epoch 511/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.7532e-04 - accuracy: 0.9977 - val_loss: 2.9667e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9928 - loss: 4.0418e-04 - val_accuracy: 0.9885 - val_loss: 2.8626e-04\n",
       "Epoch 512/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 5.3968e-04 - accuracy: 0.9931 - val_loss: 4.3854e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9928 - loss: 4.2761e-04 - val_accuracy: 0.9885 - val_loss: 5.1524e-04\n",
       "Epoch 513/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4853e-04 - accuracy: 0.9948 - val_loss: 6.8037e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9977 - loss: 5.3709e-04 - val_accuracy: 0.9885 - val_loss: 4.1070e-04\n",
       "Epoch 514/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5738e-04 - accuracy: 0.9960 - val_loss: 5.9743e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9984 - loss: 3.8829e-04 - val_accuracy: 0.9770 - val_loss: 4.6655e-04\n",
       "Epoch 515/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9029e-04 - accuracy: 0.9937 - val_loss: 7.2875e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 4.3153e-04 - val_accuracy: 0.9885 - val_loss: 3.4449e-04\n",
       "Epoch 516/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9719e-04 - accuracy: 0.9960 - val_loss: 4.8500e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9933 - loss: 3.7855e-04 - val_accuracy: 0.9885 - val_loss: 2.8237e-04\n",
       "Epoch 517/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.8401e-04 - accuracy: 0.9954 - val_loss: 4.1328e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9935 - loss: 4.0937e-04 - val_accuracy: 0.9885 - val_loss: 4.1906e-04\n",
       "Epoch 518/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.6281e-04 - accuracy: 0.9971 - val_loss: 5.8436e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9974 - loss: 4.0384e-04 - val_accuracy: 0.9885 - val_loss: 5.3929e-04\n",
       "Epoch 519/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3585e-04 - accuracy: 0.9942 - val_loss: 3.5340e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9916 - loss: 4.5719e-04 - val_accuracy: 0.9885 - val_loss: 3.3896e-04\n",
       "Epoch 520/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3018e-04 - accuracy: 0.9925 - val_loss: 4.3575e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9962 - loss: 4.1570e-04 - val_accuracy: 1.0000 - val_loss: 3.9349e-04\n",
       "Epoch 521/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5464e-04 - accuracy: 0.9919 - val_loss: 4.6626e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9928 - loss: 4.1636e-04 - val_accuracy: 1.0000 - val_loss: 4.3101e-04\n",
       "Epoch 522/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4623e-04 - accuracy: 0.9954 - val_loss: 4.2333e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9940 - loss: 4.3991e-04 - val_accuracy: 1.0000 - val_loss: 5.7035e-04\n",
       "Epoch 523/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9218e-04 - accuracy: 0.9971 - val_loss: 4.7376e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9930 - loss: 4.1944e-04 - val_accuracy: 1.0000 - val_loss: 2.9599e-04\n",
       "Epoch 524/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.3822e-04 - accuracy: 0.9937 - val_loss: 5.7866e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9966 - loss: 4.1478e-04 - val_accuracy: 0.9885 - val_loss: 4.6256e-04\n",
       "Epoch 525/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9621e-04 - accuracy: 0.9914 - val_loss: 6.2264e-04 - val_accuracy: 0.9885\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9976 - loss: 4.2199e-04 - val_accuracy: 1.0000 - val_loss: 2.9587e-04\n",
       "Epoch 526/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5987e-04 - accuracy: 0.9948 - val_loss: 5.5992e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9981 - loss: 4.7101e-04 - val_accuracy: 0.9770 - val_loss: 4.1784e-04\n",
       "Epoch 527/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4931e-04 - accuracy: 0.9954 - val_loss: 4.6903e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9964 - loss: 4.2270e-04 - val_accuracy: 1.0000 - val_loss: 2.9521e-04\n",
       "Epoch 528/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4529e-04 - accuracy: 0.9937 - val_loss: 3.6235e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9936 - loss: 4.1845e-04 - val_accuracy: 0.9885 - val_loss: 4.6690e-04\n",
       "Epoch 529/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3937e-04 - accuracy: 0.9948 - val_loss: 4.9127e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9960 - loss: 4.5558e-04 - val_accuracy: 0.9885 - val_loss: 2.9717e-04\n",
       "Epoch 530/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9058e-04 - accuracy: 0.9919 - val_loss: 4.7046e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9958 - loss: 3.7303e-04 - val_accuracy: 0.9885 - val_loss: 5.0630e-04\n",
       "Epoch 531/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.1365e-04 - accuracy: 0.9948 - val_loss: 5.1283e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9985 - loss: 4.6121e-04 - val_accuracy: 1.0000 - val_loss: 3.3174e-04\n",
       "Epoch 532/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4826e-04 - accuracy: 0.9931 - val_loss: 8.2784e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9975 - loss: 4.2463e-04 - val_accuracy: 0.9770 - val_loss: 2.6001e-04\n",
       "Epoch 533/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.4553e-04 - accuracy: 0.9977 - val_loss: 4.7095e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9915 - loss: 3.9712e-04 - val_accuracy: 0.9885 - val_loss: 4.0892e-04\n",
       "Epoch 534/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9168e-04 - accuracy: 0.9942 - val_loss: 3.9985e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9951 - loss: 3.8659e-04 - val_accuracy: 0.9885 - val_loss: 3.7450e-04\n",
       "Epoch 535/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.1159e-04 - accuracy: 0.9971 - val_loss: 4.2947e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9981 - loss: 3.8129e-04 - val_accuracy: 1.0000 - val_loss: 3.0691e-04\n",
       "Epoch 536/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.6121e-04 - accuracy: 0.9925 - val_loss: 2.9386e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9964 - loss: 3.8454e-04 - val_accuracy: 1.0000 - val_loss: 2.9445e-04\n",
       "Epoch 537/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.2434e-04 - accuracy: 0.9948 - val_loss: 5.7078e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9940 - loss: 3.8155e-04 - val_accuracy: 1.0000 - val_loss: 6.8625e-04\n",
       "Epoch 538/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.9356e-04 - accuracy: 0.9942 - val_loss: 4.8310e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9947 - loss: 3.7746e-04 - val_accuracy: 1.0000 - val_loss: 3.5530e-04\n",
       "Epoch 539/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4420e-04 - accuracy: 0.9948 - val_loss: 5.5065e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9973 - loss: 3.7783e-04 - val_accuracy: 0.9885 - val_loss: 3.3315e-04\n",
       "Epoch 540/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5260e-04 - accuracy: 0.9960 - val_loss: 6.1019e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9983 - loss: 3.6991e-04 - val_accuracy: 1.0000 - val_loss: 4.0494e-04\n",
       "Epoch 541/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8812e-04 - accuracy: 0.9914 - val_loss: 3.6189e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9967 - loss: 4.0602e-04 - val_accuracy: 0.9885 - val_loss: 3.2415e-04\n",
       "Epoch 542/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0332e-04 - accuracy: 0.9954 - val_loss: 5.2949e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 7ms/step - accuracy: 0.9969 - loss: 3.8467e-04 - val_accuracy: 1.0000 - val_loss: 4.1848e-04\n",
       "Epoch 543/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4346e-04 - accuracy: 0.9925 - val_loss: 4.7964e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9978 - loss: 4.1921e-04 - val_accuracy: 0.9885 - val_loss: 4.2761e-04\n",
       "Epoch 544/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5922e-04 - accuracy: 0.9919 - val_loss: 4.7479e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9952 - loss: 3.6985e-04 - val_accuracy: 0.9885 - val_loss: 2.2219e-04\n",
       "Epoch 545/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9416e-04 - accuracy: 0.9965 - val_loss: 3.4183e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9970 - loss: 3.5405e-04 - val_accuracy: 0.9885 - val_loss: 2.3305e-04\n",
       "Epoch 546/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4315e-04 - accuracy: 0.9942 - val_loss: 6.8165e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9939 - loss: 3.9824e-04 - val_accuracy: 1.0000 - val_loss: 2.5259e-04\n",
       "Epoch 547/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.4505e-04 - accuracy: 0.9960 - val_loss: 6.3918e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9940 - loss: 3.7190e-04 - val_accuracy: 0.9885 - val_loss: 3.8930e-04\n",
       "Epoch 548/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9909e-04 - accuracy: 0.9948 - val_loss: 5.0967e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9927 - loss: 3.8333e-04 - val_accuracy: 0.9885 - val_loss: 3.9059e-04\n",
       "Epoch 549/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4614e-04 - accuracy: 0.9948 - val_loss: 4.3894e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9952 - loss: 4.1800e-04 - val_accuracy: 1.0000 - val_loss: 3.2366e-04\n",
       "Epoch 550/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3518e-04 - accuracy: 0.9942 - val_loss: 4.2508e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9968 - loss: 4.2336e-04 - val_accuracy: 1.0000 - val_loss: 2.9384e-04\n",
       "Epoch 551/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6491e-04 - accuracy: 0.9948 - val_loss: 5.3952e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9964 - loss: 3.7072e-04 - val_accuracy: 0.9770 - val_loss: 3.2307e-04\n",
       "Epoch 552/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0780e-04 - accuracy: 0.9925 - val_loss: 6.8800e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9909 - loss: 3.6298e-04 - val_accuracy: 0.9885 - val_loss: 5.0200e-04\n",
       "Epoch 553/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9805e-04 - accuracy: 0.9948 - val_loss: 4.0953e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9970 - loss: 4.2473e-04 - val_accuracy: 1.0000 - val_loss: 2.8067e-04\n",
       "Epoch 554/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3396e-04 - accuracy: 0.9960 - val_loss: 4.5136e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9969 - loss: 3.6352e-04 - val_accuracy: 1.0000 - val_loss: 3.6674e-04\n",
       "Epoch 555/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8988e-04 - accuracy: 0.9948 - val_loss: 5.5366e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9970 - loss: 3.6129e-04 - val_accuracy: 1.0000 - val_loss: 2.7142e-04\n",
       "Epoch 556/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.2895e-04 - accuracy: 0.9971 - val_loss: 6.6711e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9926 - loss: 3.7019e-04 - val_accuracy: 1.0000 - val_loss: 2.7224e-04\n",
       "Epoch 557/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7494e-04 - accuracy: 0.9965 - val_loss: 5.9214e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9946 - loss: 3.6107e-04 - val_accuracy: 1.0000 - val_loss: 3.2166e-04\n",
       "Epoch 558/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9582e-04 - accuracy: 0.9937 - val_loss: 3.8112e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9929 - loss: 3.6339e-04 - val_accuracy: 0.9770 - val_loss: 4.4845e-04\n",
       "Epoch 559/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9429e-04 - accuracy: 0.9954 - val_loss: 7.6287e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9970 - loss: 3.9516e-04 - val_accuracy: 1.0000 - val_loss: 2.0007e-04\n",
       "Epoch 560/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5386e-04 - accuracy: 0.9937 - val_loss: 5.3557e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9936 - loss: 4.0001e-04 - val_accuracy: 1.0000 - val_loss: 2.8674e-04\n",
       "Epoch 561/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.6776e-04 - accuracy: 0.9948 - val_loss: 4.8595e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9947 - loss: 3.7071e-04 - val_accuracy: 0.9770 - val_loss: 3.7468e-04\n",
       "Epoch 562/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.8714e-04 - accuracy: 0.9937 - val_loss: 4.5314e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9953 - loss: 4.1175e-04 - val_accuracy: 0.9885 - val_loss: 3.3121e-04\n",
       "Epoch 563/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3772e-04 - accuracy: 0.9960 - val_loss: 5.2940e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9958 - loss: 3.2688e-04 - val_accuracy: 0.9885 - val_loss: 3.3503e-04\n",
       "Epoch 564/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8248e-04 - accuracy: 0.9942 - val_loss: 5.9694e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9992 - loss: 3.6591e-04 - val_accuracy: 1.0000 - val_loss: 4.6899e-04\n",
       "Epoch 565/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.6054e-04 - accuracy: 0.9977 - val_loss: 4.4669e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9986 - loss: 3.6898e-04 - val_accuracy: 0.9885 - val_loss: 5.0517e-04\n",
       "Epoch 566/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.6184e-04 - accuracy: 0.9931 - val_loss: 4.5412e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9953 - loss: 3.4439e-04 - val_accuracy: 0.9885 - val_loss: 5.0138e-04\n",
       "Epoch 567/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 6.2740e-04 - accuracy: 0.9948 - val_loss: 4.4633e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9959 - loss: 4.0190e-04 - val_accuracy: 1.0000 - val_loss: 3.3385e-04\n",
       "Epoch 568/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.3408e-04 - accuracy: 0.9948 - val_loss: 3.2543e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9954 - loss: 3.8276e-04 - val_accuracy: 0.9885 - val_loss: 2.8190e-04\n",
       "Epoch 569/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.0252e-04 - accuracy: 0.9942 - val_loss: 3.4563e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9987 - loss: 3.2637e-04 - val_accuracy: 0.9885 - val_loss: 2.7153e-04\n",
       "Epoch 570/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.4110e-04 - accuracy: 0.9942 - val_loss: 3.3310e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9938 - loss: 3.3941e-04 - val_accuracy: 0.9885 - val_loss: 3.4941e-04\n",
       "Epoch 571/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.9494e-04 - accuracy: 0.9919 - val_loss: 4.8593e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9978 - loss: 3.2548e-04 - val_accuracy: 0.9885 - val_loss: 3.5114e-04\n",
       "Epoch 572/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.4496e-04 - accuracy: 0.9942 - val_loss: 5.6715e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9967 - loss: 3.5423e-04 - val_accuracy: 0.9885 - val_loss: 2.9994e-04\n",
       "Epoch 573/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 7.1780e-04 - accuracy: 0.9914 - val_loss: 4.7332e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9959 - loss: 3.8089e-04 - val_accuracy: 0.9885 - val_loss: 2.7300e-04\n",
       "Epoch 574/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0506e-04 - accuracy: 0.9965 - val_loss: 4.1484e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9927 - loss: 3.7092e-04 - val_accuracy: 1.0000 - val_loss: 3.5273e-04\n",
       "Epoch 575/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6425e-04 - accuracy: 0.9977 - val_loss: 4.4950e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9942 - loss: 3.9145e-04 - val_accuracy: 0.9885 - val_loss: 2.8704e-04\n",
       "Epoch 576/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8526e-04 - accuracy: 0.9937 - val_loss: 6.2769e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9976 - loss: 4.0237e-04 - val_accuracy: 1.0000 - val_loss: 3.5498e-04\n",
       "Epoch 577/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5867e-04 - accuracy: 0.9954 - val_loss: 4.0461e-04 - val_accuracy: 1.0000\n",
-      "Epoch 578/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9733e-04 - accuracy: 0.9931 - val_loss: 5.1126e-04 - val_accuracy: 1.0000\n",
-      "Epoch 579/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.1576e-04 - accuracy: 0.9937 - val_loss: 5.5057e-04 - val_accuracy: 1.0000\n",
-      "Epoch 580/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9269e-04 - accuracy: 0.9937 - val_loss: 4.5154e-04 - val_accuracy: 1.0000\n",
-      "Epoch 581/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.5228e-04 - accuracy: 0.9948 - val_loss: 4.6278e-04 - val_accuracy: 1.0000\n",
-      "Epoch 582/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7058e-04 - accuracy: 0.9942 - val_loss: 3.7197e-04 - val_accuracy: 1.0000\n",
-      "Epoch 583/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8473e-04 - accuracy: 0.9954 - val_loss: 2.9253e-04 - val_accuracy: 1.0000\n",
-      "Epoch 584/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6732e-04 - accuracy: 0.9948 - val_loss: 7.1873e-04 - val_accuracy: 1.0000\n",
-      "Epoch 585/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0664e-04 - accuracy: 0.9925 - val_loss: 4.3005e-04 - val_accuracy: 1.0000\n",
-      "Epoch 586/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4846e-04 - accuracy: 0.9954 - val_loss: 6.4249e-04 - val_accuracy: 1.0000\n",
-      "Epoch 587/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4800e-04 - accuracy: 0.9954 - val_loss: 3.8982e-04 - val_accuracy: 1.0000\n",
-      "Epoch 588/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6383e-04 - accuracy: 0.9942 - val_loss: 6.0243e-04 - val_accuracy: 1.0000\n",
-      "Epoch 589/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6612e-04 - accuracy: 0.9965 - val_loss: 3.7390e-04 - val_accuracy: 1.0000\n",
-      "Epoch 590/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.3607e-04 - accuracy: 0.9977 - val_loss: 4.0699e-04 - val_accuracy: 1.0000\n",
-      "Epoch 591/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4991e-04 - accuracy: 0.9954 - val_loss: 3.9525e-04 - val_accuracy: 1.0000\n",
-      "Epoch 592/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.6367e-04 - accuracy: 0.9931 - val_loss: 5.8079e-04 - val_accuracy: 1.0000\n",
-      "Epoch 593/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.0078e-04 - accuracy: 0.9942 - val_loss: 4.3796e-04 - val_accuracy: 1.0000\n",
-      "Epoch 594/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9558e-04 - accuracy: 0.9965 - val_loss: 3.4413e-04 - val_accuracy: 1.0000\n",
-      "Epoch 595/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.1718e-04 - accuracy: 0.9942 - val_loss: 6.2046e-04 - val_accuracy: 1.0000\n",
-      "Epoch 596/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5112e-04 - accuracy: 0.9931 - val_loss: 4.9392e-04 - val_accuracy: 1.0000\n",
-      "Epoch 597/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.2614e-04 - accuracy: 0.9925 - val_loss: 5.0621e-04 - val_accuracy: 1.0000\n",
-      "Epoch 598/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.1615e-04 - accuracy: 0.9937 - val_loss: 7.6910e-04 - val_accuracy: 1.0000\n",
-      "Epoch 599/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4745e-04 - accuracy: 0.9948 - val_loss: 7.2341e-04 - val_accuracy: 1.0000\n",
-      "Epoch 600/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8949e-04 - accuracy: 0.9948 - val_loss: 4.2101e-04 - val_accuracy: 1.0000\n",
-      "Epoch 601/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.5052e-04 - accuracy: 0.9931 - val_loss: 4.5919e-04 - val_accuracy: 1.0000\n",
-      "Epoch 602/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8266e-04 - accuracy: 0.9954 - val_loss: 4.9576e-04 - val_accuracy: 1.0000\n",
-      "Epoch 603/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0739e-04 - accuracy: 0.9925 - val_loss: 3.8538e-04 - val_accuracy: 1.0000\n",
-      "Epoch 604/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0232e-04 - accuracy: 0.9942 - val_loss: 5.0681e-04 - val_accuracy: 1.0000\n",
-      "Epoch 605/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.5854e-04 - accuracy: 0.9931 - val_loss: 3.2557e-04 - val_accuracy: 1.0000\n",
-      "Epoch 606/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7950e-04 - accuracy: 0.9948 - val_loss: 5.0947e-04 - val_accuracy: 1.0000\n",
-      "Epoch 607/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4898e-04 - accuracy: 0.9965 - val_loss: 4.7209e-04 - val_accuracy: 1.0000\n",
-      "Epoch 608/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6126e-04 - accuracy: 0.9931 - val_loss: 3.0669e-04 - val_accuracy: 1.0000\n",
-      "Epoch 609/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1479e-04 - accuracy: 0.9960 - val_loss: 3.4483e-04 - val_accuracy: 1.0000\n",
-      "Epoch 610/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6733e-04 - accuracy: 0.9960 - val_loss: 3.7777e-04 - val_accuracy: 1.0000\n",
-      "Epoch 611/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3892e-04 - accuracy: 0.9983 - val_loss: 3.6352e-04 - val_accuracy: 1.0000\n",
-      "Epoch 612/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5167e-04 - accuracy: 0.9977 - val_loss: 5.4879e-04 - val_accuracy: 1.0000\n",
-      "Epoch 613/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9691e-04 - accuracy: 0.9948 - val_loss: 4.1026e-04 - val_accuracy: 1.0000\n",
-      "Epoch 614/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.6389e-04 - accuracy: 0.9942 - val_loss: 3.1889e-04 - val_accuracy: 1.0000\n",
-      "Epoch 615/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7549e-04 - accuracy: 0.9965 - val_loss: 3.2853e-04 - val_accuracy: 1.0000\n",
-      "Epoch 616/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.4556e-04 - accuracy: 0.9971 - val_loss: 4.0605e-04 - val_accuracy: 1.0000\n",
-      "Epoch 617/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0976e-04 - accuracy: 0.9948 - val_loss: 4.6128e-04 - val_accuracy: 1.0000\n",
-      "Epoch 618/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.1375e-04 - accuracy: 0.9948 - val_loss: 5.2925e-04 - val_accuracy: 1.0000\n",
-      "Epoch 619/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9307e-04 - accuracy: 0.9925 - val_loss: 4.9549e-04 - val_accuracy: 1.0000\n",
-      "Epoch 620/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.6937e-04 - accuracy: 0.9942 - val_loss: 3.0204e-04 - val_accuracy: 1.0000\n",
-      "Epoch 621/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 5.2463e-04 - accuracy: 0.9954 - val_loss: 3.6759e-04 - val_accuracy: 1.0000\n",
-      "Epoch 622/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8767e-04 - accuracy: 0.9971 - val_loss: 3.5927e-04 - val_accuracy: 1.0000\n",
-      "Epoch 623/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9450e-04 - accuracy: 0.9954 - val_loss: 4.0536e-04 - val_accuracy: 1.0000\n",
-      "Epoch 624/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5912e-04 - accuracy: 0.9919 - val_loss: 4.5793e-04 - val_accuracy: 1.0000\n",
-      "Epoch 625/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3049e-04 - accuracy: 0.9942 - val_loss: 4.1004e-04 - val_accuracy: 1.0000\n",
-      "Epoch 626/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3414e-04 - accuracy: 0.9954 - val_loss: 4.8625e-04 - val_accuracy: 1.0000\n",
-      "Epoch 627/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.2933e-04 - accuracy: 0.9965 - val_loss: 4.4867e-04 - val_accuracy: 1.0000\n",
-      "Epoch 628/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.1573e-04 - accuracy: 0.9931 - val_loss: 7.4793e-04 - val_accuracy: 1.0000\n",
-      "Epoch 629/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5720e-04 - accuracy: 0.9954 - val_loss: 3.6485e-04 - val_accuracy: 1.0000\n",
-      "Epoch 630/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5776e-04 - accuracy: 0.9971 - val_loss: 3.6713e-04 - val_accuracy: 1.0000\n",
-      "Epoch 631/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3096e-04 - accuracy: 0.9960 - val_loss: 4.8155e-04 - val_accuracy: 1.0000\n",
-      "Epoch 632/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3892e-04 - accuracy: 0.9942 - val_loss: 4.0100e-04 - val_accuracy: 1.0000\n",
-      "Epoch 633/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3892e-04 - accuracy: 0.9977 - val_loss: 5.1844e-04 - val_accuracy: 1.0000\n",
-      "Epoch 634/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2510e-04 - accuracy: 0.9954 - val_loss: 4.3272e-04 - val_accuracy: 1.0000\n",
-      "Epoch 635/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2081e-04 - accuracy: 0.9948 - val_loss: 3.9679e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9980 - loss: 3.7475e-04 - val_accuracy: 0.9885 - val_loss: 4.6416e-04\n",
       "Epoch 636/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9534e-04 - accuracy: 0.9937 - val_loss: 4.6294e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9975 - loss: 3.5815e-04 - val_accuracy: 0.9885 - val_loss: 2.4328e-04\n",
       "Epoch 637/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8160e-04 - accuracy: 0.9931 - val_loss: 3.7059e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9940 - loss: 3.2755e-04 - val_accuracy: 1.0000 - val_loss: 3.2902e-04\n",
       "Epoch 638/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7199e-04 - accuracy: 0.9948 - val_loss: 4.3801e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 15ms/step - accuracy: 0.9970 - loss: 3.2204e-04 - val_accuracy: 1.0000 - val_loss: 4.3149e-04\n",
       "Epoch 639/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.7482e-04 - accuracy: 0.9948 - val_loss: 3.1577e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9934 - loss: 3.6028e-04 - val_accuracy: 1.0000 - val_loss: 1.9349e-04\n",
       "Epoch 640/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1966e-04 - accuracy: 0.9942 - val_loss: 4.6176e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 15ms/step - accuracy: 0.9968 - loss: 3.1882e-04 - val_accuracy: 1.0000 - val_loss: 2.2922e-04\n",
       "Epoch 641/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3549e-04 - accuracy: 0.9948 - val_loss: 3.9608e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9984 - loss: 3.1943e-04 - val_accuracy: 0.9770 - val_loss: 3.0492e-04\n",
       "Epoch 642/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7924e-04 - accuracy: 0.9965 - val_loss: 3.4643e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9955 - loss: 3.1737e-04 - val_accuracy: 1.0000 - val_loss: 2.0732e-04\n",
       "Epoch 643/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8232e-04 - accuracy: 0.9937 - val_loss: 4.5328e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9964 - loss: 3.1837e-04 - val_accuracy: 1.0000 - val_loss: 8.3943e-04\n",
       "Epoch 644/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2856e-04 - accuracy: 0.9954 - val_loss: 5.9541e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9964 - loss: 2.9374e-04 - val_accuracy: 1.0000 - val_loss: 1.9458e-04\n",
       "Epoch 645/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.4956e-04 - accuracy: 0.9960 - val_loss: 3.3769e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9928 - loss: 3.1120e-04 - val_accuracy: 1.0000 - val_loss: 2.7006e-04\n",
       "Epoch 646/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.9023e-04 - accuracy: 0.9965 - val_loss: 3.4405e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 1.0000 - loss: 2.9745e-04 - val_accuracy: 1.0000 - val_loss: 2.8758e-04\n",
       "Epoch 647/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 5.0574e-04 - accuracy: 0.9954 - val_loss: 5.1006e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9967 - loss: 3.9583e-04 - val_accuracy: 1.0000 - val_loss: 3.2718e-04\n",
       "Epoch 648/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.7865e-04 - accuracy: 0.9960 - val_loss: 3.2435e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 15ms/step - accuracy: 0.9987 - loss: 3.2887e-04 - val_accuracy: 1.0000 - val_loss: 5.9752e-04\n",
       "Epoch 649/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.9225e-04 - accuracy: 0.9937 - val_loss: 4.4185e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9934 - loss: 2.9656e-04 - val_accuracy: 1.0000 - val_loss: 2.3894e-04\n",
       "Epoch 650/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.9907e-04 - accuracy: 0.9954 - val_loss: 4.1936e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9980 - loss: 3.0766e-04 - val_accuracy: 0.9885 - val_loss: 3.3398e-04\n",
       "Epoch 651/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4702e-04 - accuracy: 0.9960 - val_loss: 3.6178e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9981 - loss: 3.6651e-04 - val_accuracy: 0.9885 - val_loss: 3.0440e-04\n",
       "Epoch 652/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.1142e-04 - accuracy: 0.9942 - val_loss: 3.8226e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9989 - loss: 3.1939e-04 - val_accuracy: 0.9885 - val_loss: 2.7876e-04\n",
       "Epoch 653/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4657e-04 - accuracy: 0.9971 - val_loss: 3.4001e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9944 - loss: 3.1395e-04 - val_accuracy: 1.0000 - val_loss: 2.3943e-04\n",
       "Epoch 654/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.0081e-04 - accuracy: 0.9954 - val_loss: 2.0725e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9972 - loss: 2.9693e-04 - val_accuracy: 0.9885 - val_loss: 3.2822e-04\n",
       "Epoch 655/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.2398e-04 - accuracy: 0.9948 - val_loss: 2.6823e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9985 - loss: 3.1896e-04 - val_accuracy: 0.9885 - val_loss: 3.6328e-04\n",
       "Epoch 656/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.9876e-04 - accuracy: 0.9971 - val_loss: 4.0582e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9963 - loss: 5.1075e-04 - val_accuracy: 0.9770 - val_loss: 3.2573e-04\n",
       "Epoch 657/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.0928e-04 - accuracy: 0.9931 - val_loss: 3.4866e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9964 - loss: 3.3634e-04 - val_accuracy: 0.9885 - val_loss: 3.0641e-04\n",
       "Epoch 658/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.9974e-04 - accuracy: 0.9948 - val_loss: 3.1501e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9941 - loss: 3.4208e-04 - val_accuracy: 0.9770 - val_loss: 2.1471e-04\n",
       "Epoch 659/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3693e-04 - accuracy: 0.9954 - val_loss: 5.5914e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9968 - loss: 2.8926e-04 - val_accuracy: 1.0000 - val_loss: 2.4052e-04\n",
       "Epoch 660/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.4000e-04 - accuracy: 0.9942 - val_loss: 4.7686e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9984 - loss: 3.1506e-04 - val_accuracy: 0.9885 - val_loss: 2.8255e-04\n",
       "Epoch 661/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.2370e-04 - accuracy: 0.9977 - val_loss: 4.6141e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9980 - loss: 2.8300e-04 - val_accuracy: 0.9885 - val_loss: 2.7999e-04\n",
       "Epoch 662/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.0424e-04 - accuracy: 0.9954 - val_loss: 3.9165e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - accuracy: 0.9980 - loss: 3.2274e-04 - val_accuracy: 1.0000 - val_loss: 3.8810e-04\n",
       "Epoch 663/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8473e-04 - accuracy: 0.9954 - val_loss: 3.7559e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9961 - loss: 2.8411e-04 - val_accuracy: 0.9885 - val_loss: 2.9168e-04\n",
       "Epoch 664/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7643e-04 - accuracy: 0.9931 - val_loss: 3.7440e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9947 - loss: 3.7612e-04 - val_accuracy: 1.0000 - val_loss: 3.2317e-04\n",
       "Epoch 665/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.7317e-04 - accuracy: 0.9965 - val_loss: 3.3140e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9921 - loss: 3.5925e-04 - val_accuracy: 1.0000 - val_loss: 3.7673e-04\n",
       "Epoch 666/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0684e-04 - accuracy: 0.9942 - val_loss: 2.8772e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9987 - loss: 3.3254e-04 - val_accuracy: 1.0000 - val_loss: 2.4441e-04\n",
       "Epoch 667/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.3472e-04 - accuracy: 0.9925 - val_loss: 4.8656e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9936 - loss: 3.3283e-04 - val_accuracy: 0.9885 - val_loss: 4.0815e-04\n",
       "Epoch 668/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3135e-04 - accuracy: 0.9954 - val_loss: 6.1047e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9971 - loss: 3.4300e-04 - val_accuracy: 0.9885 - val_loss: 4.5874e-04\n",
       "Epoch 669/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8682e-04 - accuracy: 0.9965 - val_loss: 4.5790e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 14ms/step - accuracy: 0.9919 - loss: 3.4651e-04 - val_accuracy: 0.9885 - val_loss: 3.3445e-04\n",
       "Epoch 670/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1384e-04 - accuracy: 0.9954 - val_loss: 4.3208e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9954 - loss: 3.0992e-04 - val_accuracy: 0.9770 - val_loss: 3.0159e-04\n",
       "Epoch 671/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 6.2928e-04 - accuracy: 0.9954 - val_loss: 2.7948e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9979 - loss: 3.4849e-04 - val_accuracy: 1.0000 - val_loss: 2.5972e-04\n",
       "Epoch 672/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.2185e-04 - accuracy: 0.9960 - val_loss: 4.4602e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 12ms/step - accuracy: 0.9944 - loss: 3.4200e-04 - val_accuracy: 1.0000 - val_loss: 2.7749e-04\n",
       "Epoch 673/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.7499e-04 - accuracy: 0.9931 - val_loss: 2.9431e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9979 - loss: 3.2345e-04 - val_accuracy: 1.0000 - val_loss: 1.9776e-04\n",
       "Epoch 674/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5220e-04 - accuracy: 0.9948 - val_loss: 2.9242e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - accuracy: 0.9985 - loss: 3.0669e-04 - val_accuracy: 1.0000 - val_loss: 2.0304e-04\n",
       "Epoch 675/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.3212e-04 - accuracy: 0.9948 - val_loss: 2.9766e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 9ms/step - accuracy: 0.9962 - loss: 3.2382e-04 - val_accuracy: 0.9770 - val_loss: 2.7848e-04\n",
       "Epoch 676/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7887e-04 - accuracy: 0.9960 - val_loss: 3.0517e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9971 - loss: 3.0848e-04 - val_accuracy: 0.9885 - val_loss: 3.1987e-04\n",
       "Epoch 677/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0078e-04 - accuracy: 0.9983 - val_loss: 3.2216e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 7ms/step - accuracy: 0.9976 - loss: 3.5695e-04 - val_accuracy: 0.9885 - val_loss: 4.9381e-04\n",
       "Epoch 678/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.9127e-04 - accuracy: 0.9960 - val_loss: 3.7476e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9956 - loss: 3.5219e-04 - val_accuracy: 1.0000 - val_loss: 2.6921e-04\n",
       "Epoch 679/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.6159e-04 - accuracy: 0.9988 - val_loss: 2.9396e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9935 - loss: 4.1803e-04 - val_accuracy: 1.0000 - val_loss: 2.0158e-04\n",
       "Epoch 680/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.3362e-04 - accuracy: 0.9960 - val_loss: 3.6776e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9978 - loss: 3.3268e-04 - val_accuracy: 1.0000 - val_loss: 7.3587e-04\n",
       "Epoch 681/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.9771e-04 - accuracy: 0.9971 - val_loss: 2.6896e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9948 - loss: 3.5313e-04 - val_accuracy: 1.0000 - val_loss: 2.6954e-04\n",
       "Epoch 682/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.7894e-04 - accuracy: 0.9965 - val_loss: 4.1595e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.9970 - loss: 3.4228e-04 - val_accuracy: 0.9885 - val_loss: 2.8583e-04\n",
       "Epoch 683/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.3630e-04 - accuracy: 0.9954 - val_loss: 2.4091e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9962 - loss: 3.0761e-04 - val_accuracy: 0.9885 - val_loss: 2.8050e-04\n",
       "Epoch 684/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0419e-04 - accuracy: 0.9983 - val_loss: 3.6992e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9962 - loss: 3.1306e-04 - val_accuracy: 0.9885 - val_loss: 4.8212e-04\n",
       "Epoch 685/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7933e-04 - accuracy: 0.9954 - val_loss: 3.1658e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9941 - loss: 3.5819e-04 - val_accuracy: 0.9885 - val_loss: 2.5594e-04\n",
       "Epoch 686/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1582e-04 - accuracy: 0.9965 - val_loss: 3.3148e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9933 - loss: 3.7295e-04 - val_accuracy: 0.9885 - val_loss: 2.7941e-04\n",
       "Epoch 687/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8746e-04 - accuracy: 0.9954 - val_loss: 3.6834e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9998 - loss: 2.9341e-04 - val_accuracy: 0.9885 - val_loss: 2.5393e-04\n",
       "Epoch 688/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1969e-04 - accuracy: 0.9971 - val_loss: 3.6462e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9982 - loss: 3.1536e-04 - val_accuracy: 0.9885 - val_loss: 2.6781e-04\n",
       "Epoch 689/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1080e-04 - accuracy: 0.9937 - val_loss: 4.5904e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9947 - loss: 3.2042e-04 - val_accuracy: 1.0000 - val_loss: 2.6733e-04\n",
       "Epoch 690/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0627e-04 - accuracy: 0.9954 - val_loss: 4.5096e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9949 - loss: 3.3773e-04 - val_accuracy: 1.0000 - val_loss: 2.3976e-04\n",
       "Epoch 691/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1270e-04 - accuracy: 0.9954 - val_loss: 4.3936e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9991 - loss: 2.9796e-04 - val_accuracy: 1.0000 - val_loss: 3.2106e-04\n",
       "Epoch 692/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8336e-04 - accuracy: 0.9988 - val_loss: 3.0204e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9978 - loss: 2.7476e-04 - val_accuracy: 1.0000 - val_loss: 2.8142e-04\n",
       "Epoch 693/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9146e-04 - accuracy: 0.9971 - val_loss: 3.4019e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9973 - loss: 3.0153e-04 - val_accuracy: 0.9885 - val_loss: 3.7178e-04\n",
       "Epoch 694/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.1968e-04 - accuracy: 0.9925 - val_loss: 4.1899e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9969 - loss: 3.1368e-04 - val_accuracy: 0.9885 - val_loss: 2.5333e-04\n",
       "Epoch 695/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.7932e-04 - accuracy: 0.9960 - val_loss: 2.5404e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9959 - loss: 3.0397e-04 - val_accuracy: 0.9885 - val_loss: 2.3120e-04\n",
       "Epoch 696/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7757e-04 - accuracy: 0.9948 - val_loss: 3.1901e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9957 - loss: 3.1623e-04 - val_accuracy: 1.0000 - val_loss: 3.0779e-04\n",
       "Epoch 697/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7410e-04 - accuracy: 0.9971 - val_loss: 3.9866e-04 - val_accuracy: 1.0000\n",
-      "Epoch 698/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3127e-04 - accuracy: 0.9965 - val_loss: 3.3849e-04 - val_accuracy: 1.0000\n",
-      "Epoch 699/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5361e-04 - accuracy: 0.9965 - val_loss: 3.6029e-04 - val_accuracy: 1.0000\n",
-      "Epoch 700/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1778e-04 - accuracy: 0.9942 - val_loss: 4.5138e-04 - val_accuracy: 1.0000\n",
-      "Epoch 701/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1913e-04 - accuracy: 0.9902 - val_loss: 4.0426e-04 - val_accuracy: 1.0000\n",
-      "Epoch 702/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4099e-04 - accuracy: 0.9948 - val_loss: 3.5883e-04 - val_accuracy: 1.0000\n",
-      "Epoch 703/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2401e-04 - accuracy: 0.9983 - val_loss: 4.5065e-04 - val_accuracy: 1.0000\n",
-      "Epoch 704/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8009e-04 - accuracy: 0.9988 - val_loss: 3.7090e-04 - val_accuracy: 1.0000\n",
-      "Epoch 705/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7816e-04 - accuracy: 0.9965 - val_loss: 3.8575e-04 - val_accuracy: 1.0000\n",
-      "Epoch 706/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.4379e-04 - accuracy: 0.9977 - val_loss: 9.6650e-04 - val_accuracy: 1.0000\n",
-      "Epoch 707/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2239e-04 - accuracy: 0.9960 - val_loss: 2.5228e-04 - val_accuracy: 1.0000\n",
-      "Epoch 708/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0147e-04 - accuracy: 0.9954 - val_loss: 3.1076e-04 - val_accuracy: 1.0000\n",
-      "Epoch 709/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3008e-04 - accuracy: 0.9937 - val_loss: 4.3054e-04 - val_accuracy: 1.0000\n",
-      "Epoch 710/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8529e-04 - accuracy: 0.9960 - val_loss: 4.3159e-04 - val_accuracy: 1.0000\n",
-      "Epoch 711/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0940e-04 - accuracy: 0.9954 - val_loss: 9.3537e-04 - val_accuracy: 1.0000\n",
-      "Epoch 712/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5420e-04 - accuracy: 0.9971 - val_loss: 4.2111e-04 - val_accuracy: 1.0000\n",
-      "Epoch 713/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8294e-04 - accuracy: 0.9965 - val_loss: 4.4528e-04 - val_accuracy: 1.0000\n",
-      "Epoch 714/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7860e-04 - accuracy: 0.9954 - val_loss: 3.3116e-04 - val_accuracy: 1.0000\n",
-      "Epoch 715/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1544e-04 - accuracy: 0.9954 - val_loss: 2.2696e-04 - val_accuracy: 1.0000\n",
-      "Epoch 716/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.4610e-04 - accuracy: 0.9960 - val_loss: 2.4307e-04 - val_accuracy: 1.0000\n",
-      "Epoch 717/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.9827e-04 - accuracy: 0.9977 - val_loss: 4.4595e-04 - val_accuracy: 1.0000\n",
-      "Epoch 718/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9398e-04 - accuracy: 0.9977 - val_loss: 4.4366e-04 - val_accuracy: 1.0000\n",
-      "Epoch 719/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.5195e-04 - accuracy: 0.9948 - val_loss: 2.7449e-04 - val_accuracy: 1.0000\n",
-      "Epoch 720/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3111e-04 - accuracy: 0.9942 - val_loss: 3.5359e-04 - val_accuracy: 1.0000\n",
-      "Epoch 721/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.3330e-04 - accuracy: 0.9948 - val_loss: 4.8398e-04 - val_accuracy: 1.0000\n",
-      "Epoch 722/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1630e-04 - accuracy: 0.9983 - val_loss: 3.5967e-04 - val_accuracy: 1.0000\n",
-      "Epoch 723/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4380e-04 - accuracy: 0.9954 - val_loss: 2.9186e-04 - val_accuracy: 1.0000\n",
-      "Epoch 724/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9626e-04 - accuracy: 0.9965 - val_loss: 2.5978e-04 - val_accuracy: 1.0000\n",
-      "Epoch 725/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1226e-04 - accuracy: 0.9954 - val_loss: 2.7840e-04 - val_accuracy: 1.0000\n",
-      "Epoch 726/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9143e-04 - accuracy: 0.9948 - val_loss: 4.4900e-04 - val_accuracy: 1.0000\n",
-      "Epoch 727/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8894e-04 - accuracy: 0.9983 - val_loss: 3.3316e-04 - val_accuracy: 1.0000\n",
-      "Epoch 728/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2084e-04 - accuracy: 0.9948 - val_loss: 5.0553e-04 - val_accuracy: 1.0000\n",
-      "Epoch 729/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.8206e-04 - accuracy: 0.9965 - val_loss: 3.7685e-04 - val_accuracy: 0.9885\n",
-      "Epoch 730/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0781e-04 - accuracy: 0.9965 - val_loss: 3.0034e-04 - val_accuracy: 1.0000\n",
-      "Epoch 731/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9088e-04 - accuracy: 0.9960 - val_loss: 3.3883e-04 - val_accuracy: 1.0000\n",
-      "Epoch 732/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8693e-04 - accuracy: 0.9948 - val_loss: 3.9664e-04 - val_accuracy: 1.0000\n",
-      "Epoch 733/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7432e-04 - accuracy: 0.9983 - val_loss: 7.7926e-04 - val_accuracy: 1.0000\n",
-      "Epoch 734/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2078e-04 - accuracy: 0.9954 - val_loss: 3.0096e-04 - val_accuracy: 1.0000\n",
-      "Epoch 735/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8176e-04 - accuracy: 0.9948 - val_loss: 3.8528e-04 - val_accuracy: 1.0000\n",
-      "Epoch 736/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7594e-04 - accuracy: 0.9971 - val_loss: 4.5310e-04 - val_accuracy: 0.9885\n",
-      "Epoch 737/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8591e-04 - accuracy: 0.9960 - val_loss: 4.2767e-04 - val_accuracy: 1.0000\n",
-      "Epoch 738/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6887e-04 - accuracy: 0.9925 - val_loss: 3.8866e-04 - val_accuracy: 1.0000\n",
-      "Epoch 739/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7293e-04 - accuracy: 0.9954 - val_loss: 3.9491e-04 - val_accuracy: 1.0000\n",
-      "Epoch 740/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.7774e-04 - accuracy: 0.9948 - val_loss: 2.9363e-04 - val_accuracy: 1.0000\n",
-      "Epoch 741/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.9420e-04 - accuracy: 0.9988 - val_loss: 2.9989e-04 - val_accuracy: 1.0000\n",
-      "Epoch 742/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.5243e-04 - accuracy: 0.9948 - val_loss: 5.2124e-04 - val_accuracy: 1.0000\n",
-      "Epoch 743/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7423e-04 - accuracy: 0.9948 - val_loss: 3.5243e-04 - val_accuracy: 1.0000\n",
-      "Epoch 744/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6012e-04 - accuracy: 0.9931 - val_loss: 3.6635e-04 - val_accuracy: 1.0000\n",
-      "Epoch 745/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9507e-04 - accuracy: 0.9948 - val_loss: 4.4608e-04 - val_accuracy: 1.0000\n",
-      "Epoch 746/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9051e-04 - accuracy: 0.9948 - val_loss: 4.7106e-04 - val_accuracy: 1.0000\n",
-      "Epoch 747/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8233e-04 - accuracy: 0.9965 - val_loss: 2.2995e-04 - val_accuracy: 1.0000\n",
-      "Epoch 748/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8732e-04 - accuracy: 0.9954 - val_loss: 4.2685e-04 - val_accuracy: 1.0000\n",
-      "Epoch 749/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5604e-04 - accuracy: 0.9960 - val_loss: 3.0002e-04 - val_accuracy: 1.0000\n",
-      "Epoch 750/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6694e-04 - accuracy: 0.9971 - val_loss: 3.6217e-04 - val_accuracy: 1.0000\n",
-      "Epoch 751/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.2675e-04 - accuracy: 0.9942 - val_loss: 2.0602e-04 - val_accuracy: 1.0000\n",
-      "Epoch 752/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.4588e-04 - accuracy: 0.9971 - val_loss: 2.6845e-04 - val_accuracy: 1.0000\n",
-      "Epoch 753/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5692e-04 - accuracy: 0.9960 - val_loss: 2.8792e-04 - val_accuracy: 1.0000\n",
-      "Epoch 754/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.8879e-04 - accuracy: 0.9937 - val_loss: 3.4340e-04 - val_accuracy: 1.0000\n",
-      "Epoch 755/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5613e-04 - accuracy: 0.9983 - val_loss: 2.5135e-04 - val_accuracy: 1.0000\n",
-      "Epoch 756/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6472e-04 - accuracy: 0.9971 - val_loss: 2.5503e-04 - val_accuracy: 1.0000\n",
-      "Epoch 757/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4807e-04 - accuracy: 0.9983 - val_loss: 2.2566e-04 - val_accuracy: 1.0000\n",
-      "Epoch 758/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.8688e-04 - accuracy: 0.9971 - val_loss: 3.5572e-04 - val_accuracy: 1.0000\n",
-      "Epoch 759/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7639e-04 - accuracy: 0.9942 - val_loss: 3.1487e-04 - val_accuracy: 1.0000\n",
-      "Epoch 760/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2965e-04 - accuracy: 0.9971 - val_loss: 3.4448e-04 - val_accuracy: 1.0000\n",
-      "Epoch 761/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.1759e-04 - accuracy: 0.9977 - val_loss: 3.1406e-04 - val_accuracy: 1.0000\n",
-      "Epoch 762/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0207e-04 - accuracy: 0.9937 - val_loss: 2.8439e-04 - val_accuracy: 1.0000\n",
-      "Epoch 763/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.7969e-04 - accuracy: 0.9948 - val_loss: 4.3676e-04 - val_accuracy: 1.0000\n",
-      "Epoch 764/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.5502e-04 - accuracy: 0.9931 - val_loss: 2.5982e-04 - val_accuracy: 1.0000\n",
-      "Epoch 765/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6185e-04 - accuracy: 0.9965 - val_loss: 3.1771e-04 - val_accuracy: 1.0000\n",
-      "Epoch 766/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6404e-04 - accuracy: 0.9931 - val_loss: 3.9458e-04 - val_accuracy: 1.0000\n",
-      "Epoch 767/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7205e-04 - accuracy: 0.9983 - val_loss: 2.5362e-04 - val_accuracy: 1.0000\n",
-      "Epoch 768/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.9445e-04 - accuracy: 0.9965 - val_loss: 3.3825e-04 - val_accuracy: 1.0000\n",
-      "Epoch 769/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.8789e-04 - accuracy: 0.9977 - val_loss: 5.1094e-04 - val_accuracy: 1.0000\n",
-      "Epoch 770/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.7722e-04 - accuracy: 0.9960 - val_loss: 3.9677e-04 - val_accuracy: 1.0000\n",
-      "Epoch 771/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6857e-04 - accuracy: 0.9977 - val_loss: 4.3820e-04 - val_accuracy: 1.0000\n",
-      "Epoch 772/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.8521e-04 - accuracy: 0.9965 - val_loss: 3.7753e-04 - val_accuracy: 1.0000\n",
-      "Epoch 773/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.3035e-04 - accuracy: 0.9954 - val_loss: 3.8490e-04 - val_accuracy: 1.0000\n",
-      "Epoch 774/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.3915e-04 - accuracy: 0.9925 - val_loss: 3.2202e-04 - val_accuracy: 1.0000\n",
-      "Epoch 775/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.8815e-04 - accuracy: 0.9948 - val_loss: 3.2526e-04 - val_accuracy: 1.0000\n",
-      "Epoch 776/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.7223e-04 - accuracy: 0.9937 - val_loss: 3.4640e-04 - val_accuracy: 1.0000\n",
-      "Epoch 777/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.6796e-04 - accuracy: 0.9994 - val_loss: 2.6859e-04 - val_accuracy: 1.0000\n",
-      "Epoch 778/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.2039e-04 - accuracy: 0.9977 - val_loss: 3.6869e-04 - val_accuracy: 1.0000\n",
-      "Epoch 779/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.2623e-04 - accuracy: 0.9977 - val_loss: 2.5993e-04 - val_accuracy: 1.0000\n",
-      "Epoch 780/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.4649e-04 - accuracy: 0.9954 - val_loss: 3.0070e-04 - val_accuracy: 1.0000\n",
-      "Epoch 781/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.9115e-04 - accuracy: 0.9971 - val_loss: 3.7552e-04 - val_accuracy: 1.0000\n",
-      "Epoch 782/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.8936e-04 - accuracy: 0.9965 - val_loss: 5.1321e-04 - val_accuracy: 1.0000\n",
-      "Epoch 783/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.5794e-04 - accuracy: 0.9965 - val_loss: 5.7428e-04 - val_accuracy: 1.0000\n",
-      "Epoch 784/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.5218e-04 - accuracy: 0.9971 - val_loss: 3.1849e-04 - val_accuracy: 1.0000\n",
-      "Epoch 785/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6675e-04 - accuracy: 0.9965 - val_loss: 3.1309e-04 - val_accuracy: 1.0000\n",
-      "Epoch 786/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0446e-04 - accuracy: 0.9931 - val_loss: 3.9143e-04 - val_accuracy: 1.0000\n",
-      "Epoch 787/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6552e-04 - accuracy: 0.9977 - val_loss: 3.5265e-04 - val_accuracy: 1.0000\n",
-      "Epoch 788/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3076e-04 - accuracy: 0.9960 - val_loss: 2.6972e-04 - val_accuracy: 1.0000\n",
-      "Epoch 789/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3849e-04 - accuracy: 0.9948 - val_loss: 3.5765e-04 - val_accuracy: 1.0000\n",
-      "Epoch 790/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0172e-04 - accuracy: 0.9948 - val_loss: 3.5507e-04 - val_accuracy: 1.0000\n",
-      "Epoch 791/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7262e-04 - accuracy: 0.9971 - val_loss: 2.5522e-04 - val_accuracy: 1.0000\n",
-      "Epoch 792/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1102e-04 - accuracy: 0.9937 - val_loss: 3.1769e-04 - val_accuracy: 1.0000\n",
-      "Epoch 793/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7180e-04 - accuracy: 0.9965 - val_loss: 2.6296e-04 - val_accuracy: 1.0000\n",
-      "Epoch 794/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.5085e-04 - accuracy: 0.9931 - val_loss: 2.9013e-04 - val_accuracy: 1.0000\n",
-      "Epoch 795/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5282e-04 - accuracy: 0.9977 - val_loss: 2.3398e-04 - val_accuracy: 1.0000\n",
-      "Epoch 796/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.9812e-04 - accuracy: 0.9948 - val_loss: 2.2528e-04 - val_accuracy: 1.0000\n",
-      "Epoch 797/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1553e-04 - accuracy: 0.9965 - val_loss: 2.4690e-04 - val_accuracy: 1.0000\n",
-      "Epoch 798/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7068e-04 - accuracy: 0.9948 - val_loss: 2.9668e-04 - val_accuracy: 1.0000\n",
-      "Epoch 799/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.0579e-04 - accuracy: 0.9977 - val_loss: 2.7118e-04 - val_accuracy: 1.0000\n",
-      "Epoch 800/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4176e-04 - accuracy: 0.9960 - val_loss: 4.3937e-04 - val_accuracy: 1.0000\n",
-      "Epoch 801/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4873e-04 - accuracy: 0.9965 - val_loss: 2.6327e-04 - val_accuracy: 1.0000\n",
-      "Epoch 802/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6228e-04 - accuracy: 0.9965 - val_loss: 3.8314e-04 - val_accuracy: 1.0000\n",
-      "Epoch 803/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.0008e-04 - accuracy: 0.9954 - val_loss: 3.5705e-04 - val_accuracy: 1.0000\n",
-      "Epoch 804/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.9606e-04 - accuracy: 0.9954 - val_loss: 3.3367e-04 - val_accuracy: 1.0000\n",
-      "Epoch 805/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.4505e-04 - accuracy: 0.9977 - val_loss: 2.3046e-04 - val_accuracy: 1.0000\n",
-      "Epoch 806/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.4519e-04 - accuracy: 0.9948 - val_loss: 4.7606e-04 - val_accuracy: 1.0000\n",
-      "Epoch 807/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2667e-04 - accuracy: 0.9960 - val_loss: 3.6245e-04 - val_accuracy: 1.0000\n",
-      "Epoch 808/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.6393e-04 - accuracy: 0.9983 - val_loss: 4.8537e-04 - val_accuracy: 1.0000\n",
-      "Epoch 809/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.5129e-04 - accuracy: 0.9971 - val_loss: 3.8335e-04 - val_accuracy: 1.0000\n",
-      "Epoch 810/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.4196e-04 - accuracy: 0.9965 - val_loss: 3.2076e-04 - val_accuracy: 1.0000\n",
-      "Epoch 811/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2506e-04 - accuracy: 0.9971 - val_loss: 2.9116e-04 - val_accuracy: 1.0000\n",
-      "Epoch 812/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.3945e-04 - accuracy: 0.9983 - val_loss: 2.5072e-04 - val_accuracy: 1.0000\n",
-      "Epoch 813/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.8442e-04 - accuracy: 0.9954 - val_loss: 2.7099e-04 - val_accuracy: 1.0000\n",
-      "Epoch 814/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6546e-04 - accuracy: 0.9971 - val_loss: 3.8282e-04 - val_accuracy: 1.0000\n",
-      "Epoch 815/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5750e-04 - accuracy: 0.9965 - val_loss: 3.4355e-04 - val_accuracy: 1.0000\n",
-      "Epoch 816/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6557e-04 - accuracy: 0.9960 - val_loss: 3.4452e-04 - val_accuracy: 1.0000\n",
-      "Epoch 817/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.1164e-04 - accuracy: 0.9983 - val_loss: 3.0951e-04 - val_accuracy: 1.0000\n",
-      "Epoch 818/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.8716e-04 - accuracy: 0.9971 - val_loss: 3.5538e-04 - val_accuracy: 1.0000\n",
-      "Epoch 819/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.6424e-04 - accuracy: 0.9971 - val_loss: 2.6973e-04 - val_accuracy: 1.0000\n",
-      "Epoch 820/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2603e-04 - accuracy: 0.9960 - val_loss: 3.0852e-04 - val_accuracy: 1.0000\n",
-      "Epoch 821/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3538e-04 - accuracy: 0.9965 - val_loss: 2.7806e-04 - val_accuracy: 1.0000\n",
-      "Epoch 822/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.5772e-04 - accuracy: 0.9994 - val_loss: 2.8825e-04 - val_accuracy: 1.0000\n",
-      "Epoch 823/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.3470e-04 - accuracy: 0.9937 - val_loss: 2.7335e-04 - val_accuracy: 1.0000\n",
-      "Epoch 824/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6646e-04 - accuracy: 0.9960 - val_loss: 3.4943e-04 - val_accuracy: 1.0000\n",
-      "Epoch 825/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2433e-04 - accuracy: 0.9960 - val_loss: 2.9275e-04 - val_accuracy: 1.0000\n",
-      "Epoch 826/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.7917e-04 - accuracy: 0.9948 - val_loss: 3.1348e-04 - val_accuracy: 1.0000\n",
-      "Epoch 827/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.6879e-04 - accuracy: 0.9960 - val_loss: 2.5459e-04 - val_accuracy: 1.0000\n",
-      "Epoch 828/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3995e-04 - accuracy: 0.9954 - val_loss: 3.2556e-04 - val_accuracy: 1.0000\n",
-      "Epoch 829/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5231e-04 - accuracy: 0.9960 - val_loss: 3.0659e-04 - val_accuracy: 1.0000\n",
-      "Epoch 830/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 4.1308e-04 - accuracy: 0.9954 - val_loss: 2.9612e-04 - val_accuracy: 1.0000\n",
-      "Epoch 831/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2478e-04 - accuracy: 0.9971 - val_loss: 2.6542e-04 - val_accuracy: 1.0000\n",
-      "Epoch 832/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5378e-04 - accuracy: 0.9942 - val_loss: 2.8422e-04 - val_accuracy: 1.0000\n",
-      "Epoch 833/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4036e-04 - accuracy: 0.9960 - val_loss: 2.7255e-04 - val_accuracy: 1.0000\n",
-      "Epoch 834/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4671e-04 - accuracy: 0.9954 - val_loss: 2.6469e-04 - val_accuracy: 1.0000\n",
-      "Epoch 835/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6868e-04 - accuracy: 0.9937 - val_loss: 3.1666e-04 - val_accuracy: 1.0000\n",
-      "Epoch 836/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3590e-04 - accuracy: 0.9948 - val_loss: 2.7592e-04 - val_accuracy: 1.0000\n",
-      "Epoch 837/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6516e-04 - accuracy: 0.9965 - val_loss: 3.5529e-04 - val_accuracy: 1.0000\n",
-      "Epoch 838/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.4703e-04 - accuracy: 0.9954 - val_loss: 3.2269e-04 - val_accuracy: 1.0000\n",
-      "Epoch 839/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2476e-04 - accuracy: 0.9942 - val_loss: 2.2057e-04 - val_accuracy: 1.0000\n",
-      "Epoch 840/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3074e-04 - accuracy: 0.9971 - val_loss: 3.2890e-04 - val_accuracy: 1.0000\n",
-      "Epoch 841/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3922e-04 - accuracy: 0.9942 - val_loss: 2.1966e-04 - val_accuracy: 1.0000\n",
-      "Epoch 842/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2207e-04 - accuracy: 0.9954 - val_loss: 2.6204e-04 - val_accuracy: 1.0000\n",
-      "Epoch 843/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3342e-04 - accuracy: 0.9977 - val_loss: 3.0934e-04 - val_accuracy: 1.0000\n",
-      "Epoch 844/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0245e-04 - accuracy: 0.9971 - val_loss: 2.2048e-04 - val_accuracy: 1.0000\n",
-      "Epoch 845/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.5431e-04 - accuracy: 0.9960 - val_loss: 3.4647e-04 - val_accuracy: 1.0000\n",
-      "Epoch 846/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.1803e-04 - accuracy: 0.9948 - val_loss: 2.9485e-04 - val_accuracy: 1.0000\n",
-      "Epoch 847/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.7308e-04 - accuracy: 0.9942 - val_loss: 5.0096e-04 - val_accuracy: 1.0000\n",
-      "Epoch 848/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6771e-04 - accuracy: 0.9960 - val_loss: 2.8079e-04 - val_accuracy: 1.0000\n",
-      "Epoch 849/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.7070e-04 - accuracy: 0.9954 - val_loss: 2.6906e-04 - val_accuracy: 1.0000\n",
-      "Epoch 850/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.3598e-04 - accuracy: 0.9948 - val_loss: 4.2945e-04 - val_accuracy: 1.0000\n",
-      "Epoch 851/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2482e-04 - accuracy: 0.9971 - val_loss: 3.1104e-04 - val_accuracy: 1.0000\n",
-      "Epoch 852/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2806e-04 - accuracy: 0.9971 - val_loss: 3.8983e-04 - val_accuracy: 1.0000\n",
-      "Epoch 853/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.4577e-04 - accuracy: 0.9994 - val_loss: 2.6627e-04 - val_accuracy: 1.0000\n",
-      "Epoch 854/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2753e-04 - accuracy: 0.9954 - val_loss: 3.0567e-04 - val_accuracy: 1.0000\n",
-      "Epoch 855/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 4.1087e-04 - accuracy: 0.9954 - val_loss: 2.7970e-04 - val_accuracy: 1.0000\n",
-      "Epoch 856/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.1780e-04 - accuracy: 0.9977 - val_loss: 3.0900e-04 - val_accuracy: 1.0000\n",
-      "Epoch 857/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.1459e-04 - accuracy: 0.9965 - val_loss: 2.5772e-04 - val_accuracy: 1.0000\n",
-      "Epoch 858/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2680e-04 - accuracy: 0.9942 - val_loss: 2.4931e-04 - val_accuracy: 1.0000\n",
-      "Epoch 859/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2342e-04 - accuracy: 0.9977 - val_loss: 2.8154e-04 - val_accuracy: 1.0000\n",
-      "Epoch 860/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.4723e-04 - accuracy: 0.9971 - val_loss: 2.2518e-04 - val_accuracy: 1.0000\n",
-      "Epoch 861/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.4366e-04 - accuracy: 0.9960 - val_loss: 2.8507e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9977 - loss: 2.5166e-04 - val_accuracy: 0.9885 - val_loss: 1.9895e-04\n",
       "Epoch 862/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2711e-04 - accuracy: 0.9960 - val_loss: 3.2914e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 2.7057e-04 - val_accuracy: 1.0000 - val_loss: 2.1390e-04\n",
       "Epoch 863/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2358e-04 - accuracy: 0.9948 - val_loss: 2.7713e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9989 - loss: 2.4482e-04 - val_accuracy: 0.9885 - val_loss: 1.9001e-04\n",
       "Epoch 864/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0768e-04 - accuracy: 0.9960 - val_loss: 3.2966e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9968 - loss: 2.4495e-04 - val_accuracy: 0.9885 - val_loss: 2.6835e-04\n",
       "Epoch 865/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2166e-04 - accuracy: 0.9948 - val_loss: 3.0500e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9975 - loss: 2.7962e-04 - val_accuracy: 1.0000 - val_loss: 1.7040e-04\n",
       "Epoch 866/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6810e-04 - accuracy: 0.9977 - val_loss: 2.6470e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9948 - loss: 2.5066e-04 - val_accuracy: 0.9885 - val_loss: 3.4792e-04\n",
       "Epoch 867/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3910e-04 - accuracy: 0.9983 - val_loss: 2.4215e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9947 - loss: 3.6324e-04 - val_accuracy: 0.9885 - val_loss: 2.3242e-04\n",
       "Epoch 868/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0680e-04 - accuracy: 0.9948 - val_loss: 2.3604e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9956 - loss: 2.7345e-04 - val_accuracy: 1.0000 - val_loss: 2.9475e-04\n",
       "Epoch 869/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0926e-04 - accuracy: 0.9954 - val_loss: 4.5029e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9957 - loss: 2.6300e-04 - val_accuracy: 1.0000 - val_loss: 2.6841e-04\n",
       "Epoch 870/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3996e-04 - accuracy: 0.9983 - val_loss: 4.9396e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9992 - loss: 2.6668e-04 - val_accuracy: 1.0000 - val_loss: 2.0330e-04\n",
       "Epoch 871/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.2044e-04 - accuracy: 0.9994 - val_loss: 2.7723e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9991 - loss: 2.6265e-04 - val_accuracy: 1.0000 - val_loss: 2.6838e-04\n",
       "Epoch 872/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.9286e-04 - accuracy: 0.9988 - val_loss: 2.5093e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9975 - loss: 2.6181e-04 - val_accuracy: 1.0000 - val_loss: 1.5571e-04\n",
       "Epoch 873/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4167e-04 - accuracy: 0.9954 - val_loss: 2.5312e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 2.5363e-04 - val_accuracy: 1.0000 - val_loss: 2.2385e-04\n",
       "Epoch 874/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.3383e-04 - accuracy: 0.9988 - val_loss: 3.6256e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9950 - loss: 2.4800e-04 - val_accuracy: 1.0000 - val_loss: 1.6493e-04\n",
       "Epoch 875/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.6981e-04 - accuracy: 0.9948 - val_loss: 2.0170e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9981 - loss: 2.5221e-04 - val_accuracy: 1.0000 - val_loss: 1.7528e-04\n",
       "Epoch 876/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1322e-04 - accuracy: 0.9937 - val_loss: 2.6641e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9964 - loss: 2.8144e-04 - val_accuracy: 1.0000 - val_loss: 2.9137e-04\n",
       "Epoch 877/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2184e-04 - accuracy: 0.9971 - val_loss: 3.0219e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9986 - loss: 2.4110e-04 - val_accuracy: 1.0000 - val_loss: 1.8438e-04\n",
       "Epoch 878/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2607e-04 - accuracy: 0.9971 - val_loss: 2.3263e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 2.4164e-04 - val_accuracy: 0.9885 - val_loss: 2.5635e-04\n",
       "Epoch 879/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.4880e-04 - accuracy: 0.9960 - val_loss: 2.7016e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9928 - loss: 2.8559e-04 - val_accuracy: 1.0000 - val_loss: 3.3507e-04\n",
       "Epoch 880/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.1858e-04 - accuracy: 0.9942 - val_loss: 2.2994e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9989 - loss: 2.6610e-04 - val_accuracy: 0.9885 - val_loss: 2.5262e-04\n",
       "Epoch 881/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.3650e-04 - accuracy: 0.9954 - val_loss: 2.8808e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9967 - loss: 2.6459e-04 - val_accuracy: 1.0000 - val_loss: 2.4528e-04\n",
       "Epoch 882/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.2550e-04 - accuracy: 0.9954 - val_loss: 3.8696e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9959 - loss: 2.5824e-04 - val_accuracy: 1.0000 - val_loss: 2.9848e-04\n",
       "Epoch 883/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.4397e-04 - accuracy: 0.9960 - val_loss: 3.3214e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9972 - loss: 3.2054e-04 - val_accuracy: 1.0000 - val_loss: 1.7469e-04\n",
       "Epoch 884/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3273e-04 - accuracy: 0.9948 - val_loss: 2.6320e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9989 - loss: 2.6899e-04 - val_accuracy: 0.9885 - val_loss: 2.0563e-04\n",
       "Epoch 885/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3581e-04 - accuracy: 0.9965 - val_loss: 2.4867e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9987 - loss: 2.5176e-04 - val_accuracy: 0.9885 - val_loss: 1.1970e-04\n",
       "Epoch 886/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.1079e-04 - accuracy: 0.9994 - val_loss: 3.4224e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9923 - loss: 2.4889e-04 - val_accuracy: 1.0000 - val_loss: 2.4875e-04\n",
       "Epoch 887/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.3441e-04 - accuracy: 0.9954 - val_loss: 3.8306e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9985 - loss: 2.6019e-04 - val_accuracy: 0.9885 - val_loss: 1.9151e-04\n",
       "Epoch 888/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.2710e-04 - accuracy: 0.9960 - val_loss: 3.3876e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9996 - loss: 2.4275e-04 - val_accuracy: 0.9885 - val_loss: 2.3361e-04\n",
       "Epoch 889/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.1335e-04 - accuracy: 0.9971 - val_loss: 2.3898e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9978 - loss: 2.5717e-04 - val_accuracy: 1.0000 - val_loss: 2.2155e-04\n",
       "Epoch 890/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 4.2494e-04 - accuracy: 0.9965 - val_loss: 3.1878e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 2.6842e-04 - val_accuracy: 0.9885 - val_loss: 1.8894e-04\n",
       "Epoch 891/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.7388e-04 - accuracy: 0.9988 - val_loss: 2.3090e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9984 - loss: 2.4931e-04 - val_accuracy: 1.0000 - val_loss: 1.7683e-04\n",
       "Epoch 892/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.2435e-04 - accuracy: 0.9977 - val_loss: 2.8665e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9998 - loss: 2.6123e-04 - val_accuracy: 1.0000 - val_loss: 2.8756e-04\n",
       "Epoch 893/1000\n",
-      "218/218 [==============================] - 2s 8ms/step - loss: 3.2952e-04 - accuracy: 0.9965 - val_loss: 1.9698e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9977 - loss: 2.4368e-04 - val_accuracy: 1.0000 - val_loss: 1.8103e-04\n",
       "Epoch 894/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.9561e-04 - accuracy: 0.9988 - val_loss: 4.3816e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9975 - loss: 2.5140e-04 - val_accuracy: 1.0000 - val_loss: 2.4448e-04\n",
       "Epoch 895/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.6668e-04 - accuracy: 0.9971 - val_loss: 5.7279e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9981 - loss: 2.7115e-04 - val_accuracy: 1.0000 - val_loss: 3.0724e-04\n",
       "Epoch 896/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3687e-04 - accuracy: 0.9954 - val_loss: 2.4898e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9987 - loss: 2.4951e-04 - val_accuracy: 0.9885 - val_loss: 2.1636e-04\n",
       "Epoch 897/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2929e-04 - accuracy: 0.9971 - val_loss: 3.1553e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9994 - loss: 2.6684e-04 - val_accuracy: 1.0000 - val_loss: 2.7508e-04\n",
       "Epoch 898/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0647e-04 - accuracy: 0.9965 - val_loss: 1.8900e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9973 - loss: 2.5605e-04 - val_accuracy: 1.0000 - val_loss: 2.2689e-04\n",
       "Epoch 899/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0626e-04 - accuracy: 0.9948 - val_loss: 3.1211e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9971 - loss: 2.5096e-04 - val_accuracy: 1.0000 - val_loss: 3.1221e-04\n",
       "Epoch 900/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.5223e-04 - accuracy: 0.9983 - val_loss: 2.3270e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9958 - loss: 3.1883e-04 - val_accuracy: 1.0000 - val_loss: 2.4078e-04\n",
       "Epoch 901/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.1334e-04 - accuracy: 0.9965 - val_loss: 2.6458e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9932 - loss: 2.5376e-04 - val_accuracy: 0.9885 - val_loss: 1.6709e-04\n",
       "Epoch 902/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0273e-04 - accuracy: 0.9965 - val_loss: 3.5261e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9968 - loss: 2.7237e-04 - val_accuracy: 1.0000 - val_loss: 2.5326e-04\n",
       "Epoch 903/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2448e-04 - accuracy: 0.9977 - val_loss: 2.9090e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9974 - loss: 2.3300e-04 - val_accuracy: 0.9885 - val_loss: 1.8067e-04\n",
       "Epoch 904/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.0633e-04 - accuracy: 0.9983 - val_loss: 2.3013e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9976 - loss: 3.1920e-04 - val_accuracy: 1.0000 - val_loss: 1.8132e-04\n",
       "Epoch 905/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1702e-04 - accuracy: 0.9983 - val_loss: 2.3236e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9957 - loss: 2.4062e-04 - val_accuracy: 1.0000 - val_loss: 4.7691e-04\n",
       "Epoch 906/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.1175e-04 - accuracy: 0.9971 - val_loss: 2.1565e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9953 - loss: 2.4925e-04 - val_accuracy: 0.9770 - val_loss: 2.7616e-04\n",
       "Epoch 907/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0543e-04 - accuracy: 0.9977 - val_loss: 2.4100e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 2.3288e-04 - val_accuracy: 1.0000 - val_loss: 2.1359e-04\n",
       "Epoch 908/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9644e-04 - accuracy: 0.9988 - val_loss: 2.5872e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9986 - loss: 2.4482e-04 - val_accuracy: 1.0000 - val_loss: 2.7974e-04\n",
       "Epoch 909/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9628e-04 - accuracy: 0.9994 - val_loss: 2.8491e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 2.7562e-04 - val_accuracy: 1.0000 - val_loss: 1.9837e-04\n",
       "Epoch 910/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0349e-04 - accuracy: 0.9988 - val_loss: 2.3636e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9938 - loss: 2.7900e-04 - val_accuracy: 1.0000 - val_loss: 1.8265e-04\n",
       "Epoch 911/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1082e-04 - accuracy: 0.9983 - val_loss: 2.3813e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9990 - loss: 2.7025e-04 - val_accuracy: 0.9885 - val_loss: 4.6715e-04\n",
       "Epoch 912/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.9135e-04 - accuracy: 0.9983 - val_loss: 2.4357e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9958 - loss: 2.7007e-04 - val_accuracy: 1.0000 - val_loss: 2.1766e-04\n",
       "Epoch 913/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.5059e-04 - accuracy: 0.9954 - val_loss: 2.5441e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9987 - loss: 2.5367e-04 - val_accuracy: 0.9885 - val_loss: 3.1464e-04\n",
       "Epoch 914/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.3279e-04 - accuracy: 0.9977 - val_loss: 3.2822e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9988 - loss: 2.6931e-04 - val_accuracy: 1.0000 - val_loss: 1.7483e-04\n",
       "Epoch 915/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.0212e-04 - accuracy: 0.9960 - val_loss: 3.6840e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9969 - loss: 2.5515e-04 - val_accuracy: 1.0000 - val_loss: 1.3889e-04\n",
       "Epoch 916/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8357e-04 - accuracy: 0.9965 - val_loss: 2.4155e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9987 - loss: 2.3078e-04 - val_accuracy: 1.0000 - val_loss: 1.8679e-04\n",
       "Epoch 917/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2005e-04 - accuracy: 0.9960 - val_loss: 2.8276e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9989 - loss: 2.7478e-04 - val_accuracy: 0.9885 - val_loss: 1.7769e-04\n",
       "Epoch 918/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2409e-04 - accuracy: 0.9965 - val_loss: 2.3052e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9960 - loss: 2.3117e-04 - val_accuracy: 1.0000 - val_loss: 2.4359e-04\n",
       "Epoch 919/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0369e-04 - accuracy: 0.9971 - val_loss: 2.7843e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9984 - loss: 2.6666e-04 - val_accuracy: 1.0000 - val_loss: 1.5932e-04\n",
       "Epoch 920/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.1377e-04 - accuracy: 0.9965 - val_loss: 2.9935e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9984 - loss: 2.7490e-04 - val_accuracy: 1.0000 - val_loss: 2.0150e-04\n",
       "Epoch 921/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.1795e-04 - accuracy: 0.9954 - val_loss: 3.6435e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9958 - loss: 2.3457e-04 - val_accuracy: 1.0000 - val_loss: 2.6457e-04\n",
       "Epoch 922/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0705e-04 - accuracy: 0.9977 - val_loss: 1.7341e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9969 - loss: 2.6420e-04 - val_accuracy: 1.0000 - val_loss: 1.9204e-04\n",
       "Epoch 923/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9563e-04 - accuracy: 0.9971 - val_loss: 1.9781e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9963 - loss: 2.5047e-04 - val_accuracy: 0.9885 - val_loss: 3.7795e-04\n",
       "Epoch 924/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9722e-04 - accuracy: 0.9971 - val_loss: 1.9630e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9954 - loss: 2.5940e-04 - val_accuracy: 1.0000 - val_loss: 2.2296e-04\n",
       "Epoch 925/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2449e-04 - accuracy: 0.9977 - val_loss: 2.6890e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9949 - loss: 2.3812e-04 - val_accuracy: 0.9885 - val_loss: 2.9513e-04\n",
       "Epoch 926/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.8093e-04 - accuracy: 0.9954 - val_loss: 4.5476e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9985 - loss: 2.3621e-04 - val_accuracy: 1.0000 - val_loss: 1.3038e-04\n",
       "Epoch 927/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9685e-04 - accuracy: 0.9994 - val_loss: 2.4907e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9999 - loss: 2.5235e-04 - val_accuracy: 0.9885 - val_loss: 2.2371e-04\n",
       "Epoch 928/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0384e-04 - accuracy: 0.9977 - val_loss: 2.4617e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9971 - loss: 2.7713e-04 - val_accuracy: 1.0000 - val_loss: 3.2415e-04\n",
       "Epoch 929/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0142e-04 - accuracy: 0.9977 - val_loss: 2.1555e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9935 - loss: 2.3577e-04 - val_accuracy: 1.0000 - val_loss: 1.7511e-04\n",
       "Epoch 930/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1922e-04 - accuracy: 0.9971 - val_loss: 2.3005e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9972 - loss: 2.4918e-04 - val_accuracy: 0.9885 - val_loss: 2.2382e-04\n",
       "Epoch 931/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1567e-04 - accuracy: 0.9977 - val_loss: 3.8086e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9950 - loss: 2.3105e-04 - val_accuracy: 1.0000 - val_loss: 2.0021e-04\n",
       "Epoch 932/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1383e-04 - accuracy: 0.9977 - val_loss: 3.2283e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9984 - loss: 2.4199e-04 - val_accuracy: 0.9885 - val_loss: 1.7133e-04\n",
       "Epoch 933/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.9252e-04 - accuracy: 0.9965 - val_loss: 3.2658e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9975 - loss: 2.2547e-04 - val_accuracy: 1.0000 - val_loss: 1.5678e-04\n",
       "Epoch 934/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.9392e-04 - accuracy: 0.9960 - val_loss: 3.1141e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9985 - loss: 2.4155e-04 - val_accuracy: 1.0000 - val_loss: 2.2886e-04\n",
       "Epoch 935/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1282e-04 - accuracy: 0.9960 - val_loss: 2.5696e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9974 - loss: 2.5925e-04 - val_accuracy: 1.0000 - val_loss: 2.2650e-04\n",
       "Epoch 936/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9568e-04 - accuracy: 0.9971 - val_loss: 2.0748e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9969 - loss: 2.3974e-04 - val_accuracy: 1.0000 - val_loss: 1.5924e-04\n",
       "Epoch 937/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 2.9754e-04 - accuracy: 0.9971 - val_loss: 2.8545e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 1.0000 - loss: 2.3234e-04 - val_accuracy: 1.0000 - val_loss: 1.2681e-04\n",
       "Epoch 938/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0944e-04 - accuracy: 0.9960 - val_loss: 2.8194e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9989 - loss: 2.3873e-04 - val_accuracy: 0.9885 - val_loss: 1.3832e-04\n",
       "Epoch 939/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2852e-04 - accuracy: 0.9977 - val_loss: 2.7185e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9961 - loss: 2.5204e-04 - val_accuracy: 1.0000 - val_loss: 3.6994e-04\n",
       "Epoch 940/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4263e-04 - accuracy: 0.9937 - val_loss: 2.4900e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9974 - loss: 2.4430e-04 - val_accuracy: 0.9885 - val_loss: 3.0494e-04\n",
       "Epoch 941/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2587e-04 - accuracy: 0.9942 - val_loss: 3.0826e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9997 - loss: 2.3338e-04 - val_accuracy: 0.9885 - val_loss: 1.8984e-04\n",
       "Epoch 942/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8023e-04 - accuracy: 0.9960 - val_loss: 3.1810e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9970 - loss: 2.4233e-04 - val_accuracy: 1.0000 - val_loss: 1.2656e-04\n",
       "Epoch 943/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0429e-04 - accuracy: 0.9965 - val_loss: 3.8607e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9984 - loss: 2.3620e-04 - val_accuracy: 0.9885 - val_loss: 2.0227e-04\n",
       "Epoch 944/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9542e-04 - accuracy: 0.9965 - val_loss: 1.7346e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9991 - loss: 2.6429e-04 - val_accuracy: 1.0000 - val_loss: 1.7693e-04\n",
       "Epoch 945/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.6888e-04 - accuracy: 0.9960 - val_loss: 3.4977e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9984 - loss: 2.4659e-04 - val_accuracy: 1.0000 - val_loss: 2.2574e-04\n",
       "Epoch 946/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0424e-04 - accuracy: 0.9983 - val_loss: 2.8646e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9941 - loss: 2.5458e-04 - val_accuracy: 0.9885 - val_loss: 1.9026e-04\n",
       "Epoch 947/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0427e-04 - accuracy: 0.9954 - val_loss: 3.2334e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9961 - loss: 2.6983e-04 - val_accuracy: 1.0000 - val_loss: 1.6564e-04\n",
       "Epoch 948/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 3.3116e-04 - accuracy: 0.9988 - val_loss: 2.8125e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9981 - loss: 2.3955e-04 - val_accuracy: 1.0000 - val_loss: 2.0609e-04\n",
       "Epoch 949/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1850e-04 - accuracy: 0.9965 - val_loss: 1.6217e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9950 - loss: 2.3433e-04 - val_accuracy: 0.9885 - val_loss: 1.5613e-04\n",
       "Epoch 950/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0036e-04 - accuracy: 0.9977 - val_loss: 2.7538e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9945 - loss: 2.3753e-04 - val_accuracy: 1.0000 - val_loss: 1.9054e-04\n",
       "Epoch 951/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0855e-04 - accuracy: 0.9971 - val_loss: 2.4354e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9997 - loss: 2.5153e-04 - val_accuracy: 1.0000 - val_loss: 2.4370e-04\n",
       "Epoch 952/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2966e-04 - accuracy: 0.9948 - val_loss: 2.1347e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9990 - loss: 2.3525e-04 - val_accuracy: 1.0000 - val_loss: 2.0455e-04\n",
       "Epoch 953/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.2328e-04 - accuracy: 0.9942 - val_loss: 2.4993e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9985 - loss: 2.4615e-04 - val_accuracy: 0.9885 - val_loss: 2.0430e-04\n",
       "Epoch 954/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0322e-04 - accuracy: 0.9977 - val_loss: 2.3235e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9986 - loss: 2.7382e-04 - val_accuracy: 0.9885 - val_loss: 2.8336e-04\n",
       "Epoch 955/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.8974e-04 - accuracy: 0.9977 - val_loss: 2.6236e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9935 - loss: 2.6270e-04 - val_accuracy: 1.0000 - val_loss: 1.9293e-04\n",
       "Epoch 956/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.8445e-04 - accuracy: 0.9971 - val_loss: 2.5837e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9957 - loss: 2.4996e-04 - val_accuracy: 1.0000 - val_loss: 1.8294e-04\n",
       "Epoch 957/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9623e-04 - accuracy: 0.9965 - val_loss: 1.7593e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9996 - loss: 2.6863e-04 - val_accuracy: 1.0000 - val_loss: 2.6731e-04\n",
       "Epoch 958/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8066e-04 - accuracy: 0.9971 - val_loss: 1.8866e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9971 - loss: 2.2186e-04 - val_accuracy: 1.0000 - val_loss: 2.1049e-04\n",
       "Epoch 959/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 2.7372e-04 - accuracy: 0.9960 - val_loss: 2.2747e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9991 - loss: 2.1235e-04 - val_accuracy: 1.0000 - val_loss: 1.8158e-04\n",
       "Epoch 960/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8639e-04 - accuracy: 0.9960 - val_loss: 4.1176e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9983 - loss: 2.4530e-04 - val_accuracy: 1.0000 - val_loss: 1.7778e-04\n",
       "Epoch 961/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8349e-04 - accuracy: 0.9988 - val_loss: 2.9082e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9961 - loss: 2.4120e-04 - val_accuracy: 1.0000 - val_loss: 1.6048e-04\n",
       "Epoch 962/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1968e-04 - accuracy: 0.9965 - val_loss: 2.3378e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 6ms/step - accuracy: 0.9992 - loss: 2.2335e-04 - val_accuracy: 1.0000 - val_loss: 2.0957e-04\n",
       "Epoch 963/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.7503e-04 - accuracy: 0.9988 - val_loss: 2.3601e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9909 - loss: 2.4349e-04 - val_accuracy: 1.0000 - val_loss: 1.5742e-04\n",
       "Epoch 964/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0662e-04 - accuracy: 0.9977 - val_loss: 2.4885e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9970 - loss: 2.3779e-04 - val_accuracy: 1.0000 - val_loss: 3.3934e-04\n",
       "Epoch 965/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1211e-04 - accuracy: 0.9960 - val_loss: 1.6848e-04 - val_accuracy: 1.0000\n",
+      "\u001b[1m218/218\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.9974 - loss: 2.6537e-04 - val_accuracy: 1.0000 - val_loss: 1.9454e-04\n",
       "Epoch 966/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1914e-04 - accuracy: 0.9960 - val_loss: 2.4354e-04 - val_accuracy: 1.0000\n",
-      "Epoch 967/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0365e-04 - accuracy: 0.9960 - val_loss: 2.9293e-04 - val_accuracy: 1.0000\n",
-      "Epoch 968/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0761e-04 - accuracy: 0.9988 - val_loss: 2.9103e-04 - val_accuracy: 1.0000\n",
-      "Epoch 969/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9068e-04 - accuracy: 0.9954 - val_loss: 2.1436e-04 - val_accuracy: 1.0000\n",
-      "Epoch 970/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0570e-04 - accuracy: 0.9965 - val_loss: 2.1062e-04 - val_accuracy: 1.0000\n",
-      "Epoch 971/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 3.0748e-04 - accuracy: 0.9971 - val_loss: 2.8172e-04 - val_accuracy: 1.0000\n",
-      "Epoch 972/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8912e-04 - accuracy: 0.9954 - val_loss: 2.8192e-04 - val_accuracy: 1.0000\n",
-      "Epoch 973/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8765e-04 - accuracy: 0.9942 - val_loss: 3.5829e-04 - val_accuracy: 1.0000\n",
-      "Epoch 974/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.7547e-04 - accuracy: 0.9988 - val_loss: 5.5770e-04 - val_accuracy: 1.0000\n",
-      "Epoch 975/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4932e-04 - accuracy: 0.9988 - val_loss: 1.9533e-04 - val_accuracy: 1.0000\n",
-      "Epoch 976/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8913e-04 - accuracy: 0.9983 - val_loss: 2.2830e-04 - val_accuracy: 1.0000\n",
-      "Epoch 977/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0576e-04 - accuracy: 0.9977 - val_loss: 2.1923e-04 - val_accuracy: 1.0000\n",
-      "Epoch 978/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.3700e-04 - accuracy: 0.9960 - val_loss: 2.3654e-04 - val_accuracy: 1.0000\n",
-      "Epoch 979/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8497e-04 - accuracy: 0.9977 - val_loss: 2.3086e-04 - val_accuracy: 1.0000\n",
-      "Epoch 980/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.7668e-04 - accuracy: 0.9965 - val_loss: 2.9371e-04 - val_accuracy: 1.0000\n",
-      "Epoch 981/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9040e-04 - accuracy: 0.9983 - val_loss: 2.3150e-04 - val_accuracy: 1.0000\n",
-      "Epoch 982/1000\n",
-      "218/218 [==============================] - 2s 7ms/step - loss: 2.9340e-04 - accuracy: 0.9965 - val_loss: 5.5181e-04 - val_accuracy: 0.9885\n",
-      "Epoch 983/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9836e-04 - accuracy: 1.0000 - val_loss: 2.0783e-04 - val_accuracy: 1.0000\n",
-      "Epoch 984/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0697e-04 - accuracy: 0.9971 - val_loss: 2.6770e-04 - val_accuracy: 1.0000\n",
-      "Epoch 985/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1978e-04 - accuracy: 0.9983 - val_loss: 2.3965e-04 - val_accuracy: 1.0000\n",
-      "Epoch 986/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0877e-04 - accuracy: 0.9954 - val_loss: 2.4908e-04 - val_accuracy: 1.0000\n",
-      "Epoch 987/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8166e-04 - accuracy: 0.9977 - val_loss: 2.8110e-04 - val_accuracy: 1.0000\n",
-      "Epoch 988/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9010e-04 - accuracy: 0.9983 - val_loss: 5.3188e-04 - val_accuracy: 1.0000\n",
-      "Epoch 989/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9478e-04 - accuracy: 0.9971 - val_loss: 2.5765e-04 - val_accuracy: 1.0000\n",
-      "Epoch 990/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9093e-04 - accuracy: 0.9971 - val_loss: 3.0247e-04 - val_accuracy: 1.0000\n",
-      "Epoch 991/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.9506e-04 - accuracy: 0.9965 - val_loss: 2.6749e-04 - val_accuracy: 1.0000\n",
-      "Epoch 992/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1771e-04 - accuracy: 0.9971 - val_loss: 1.8464e-04 - val_accuracy: 1.0000\n",
-      "Epoch 993/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.7727e-04 - accuracy: 0.9988 - val_loss: 2.0042e-04 - val_accuracy: 1.0000\n",
-      "Epoch 994/1000\n",
-      "218/218 [==============================] - 1s 7ms/step - loss: 2.9817e-04 - accuracy: 0.9971 - val_loss: 3.6228e-04 - val_accuracy: 1.0000\n",
-      "Epoch 995/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.4136e-04 - accuracy: 0.9977 - val_loss: 2.1726e-04 - val_accuracy: 1.0000\n",
-      "Epoch 996/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.8108e-04 - accuracy: 0.9965 - val_loss: 3.3840e-04 - val_accuracy: 1.0000\n",
-      "Epoch 997/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 2.7312e-04 - accuracy: 0.9971 - val_loss: 3.0644e-04 - val_accuracy: 1.0000\n",
-      "Epoch 998/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.0656e-04 - accuracy: 0.9954 - val_loss: 2.4421e-04 - val_accuracy: 1.0000\n",
-      "Epoch 999/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.2127e-04 - accuracy: 0.9965 - val_loss: 2.1933e-04 - val_accuracy: 1.0000\n",
-      "Epoch 1000/1000\n",
-      "218/218 [==============================] - 1s 6ms/step - loss: 3.1470e-04 - accuracy: 0.9965 - val_loss: 2.8634e-04 - val_accuracy: 1.0000\n"
+      "\u001b[1m 69/218\u001b[0m \u001b[32m━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9969 - loss: 2.1246e-04"
      ]
     }
    ],
@@ -2424,10 +1758,10 @@
     "if (Training_Percentage > 0):\n",
     "    train_iterator = datagen.flow(x_data, y_data, batch_size=Batch_Size)\n",
     "    validation_iterator = datagen.flow(X_test, y_test, batch_size=Batch_Size)\n",
-    "    history = model.fit_generator(train_iterator, validation_data = validation_iterator, epochs = Epoch_Anz)\n",
+    "    history = model.fit(train_iterator, validation_data = validation_iterator, epochs = Epoch_Anz)\n",
     "else:\n",
     "    train_iterator = datagen.flow(x_data, y_data, batch_size=Batch_Size)\n",
-    "    history = model.fit_generator(train_iterator, epochs = Epoch_Anz)\n"
+    "    history = model.fit(train_iterator, epochs = Epoch_Anz)\n"
    ]
   },
   {
@@ -2439,20 +1773,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "loss_ges = np.append(loss_ges, history.history['loss'])\n",
     "\n",
@@ -2483,36 +1806,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "data_resize_all\\0.8_231f631b6c58bf2e92e0a487cbd30737.jpg 0.08 -0.17905251737274264 0.25905251737274265\n",
-      "data_resize_all\\0.8_f0eace7721f12d64fff0d256b2251b44.jpg 0.08 -0.2830273677157328 0.3630273677157328\n",
-      "data_resize_all\\3.3_analog3_20201001-062503.jpg 0.32999999999999996 0.05815597771115822 0.27184402228884175\n",
-      "data_resize_all\\3.8_d8361bfca336b28adeb65f545f2e7271.jpg 0.38 -0.043022972640582635 0.42302297264058264\n",
-      "data_resize_all\\5.3_84c20b8e22b48cfdb97a445df75a4a50.jpg 0.53 0.3055505995227668 0.22444940047723322\n",
-      "data_resize_all\\5.4_c316cd3214e78ea17ee55e6c752db1da.jpg 0.54 0.35958779292330423 0.1804122070766958\n",
-      "data_resize_all\\5.5_f02eb417fef6b298060a03a203691fb2.jpg 0.55 0.24656354905797342 0.30343645094202665\n",
-      "data_resize_all\\5.6_07ce6246e6206d7a65436c016c70c097.jpg 0.5599999999999999 0.2728601757902241 0.28713982420977585\n",
-      "data_resize_all\\5.6_main_ana3_20221214-162622.jpg 0.5599999999999999 0.16128776452397028 0.39871223547602963\n",
-      "data_resize_all\\5.7_41cbbe7260501c7a937c5ab4e19a7684.jpg 0.5700000000000001 1.0378971599426146 -0.4678971599426145\n",
-      "data_resize_all\\5.7_53202090013dc227b2dc3cf24e9a978f.jpg 0.5700000000000001 0.22421067355248814 0.3457893264475119\n",
-      "data_resize_all\\5.7_53bc2d481422e0906e7c91c10e92c1af.jpg 0.5700000000000001 0.24727326263098084 0.32272673736901925\n",
-      "data_resize_all\\5.8_fa6ba127a1b88c4aacb3dfffd5fc3f34.jpg 0.58 0.2597988809313995 0.32020111906860044\n",
-      "data_resize_all\\6.1_32acefae9d4454ead084f44b91d35e38.jpg 0.61 0.792673269484568 -0.18267326948456797\n",
-      "data_resize_all\\6.1_3d0d1251befb160b3b205a7a01369fa2.jpg 0.61 1.0149490073634346 -0.40494900736343464\n",
-      "data_resize_all\\6.1_8e288076ef20955606137b8fb256e2a0.jpg 0.61 0.9535106778965144 -0.34351067789651446\n",
-      "data_resize_all\\6.2_949b857328039d56a9137a9eb70f5110.jpg 0.62 0.42093093611504123 0.19906906388495876\n",
-      "data_resize_all\\6.3_224dc58a03f4c4cbae5bd69672c05a3b.jpg 0.63 0.8926871318595123 -0.2626871318595123\n",
-      "data_resize_all\\6.4_8dfbb1e54334c23791c2247db53ae50e.jpg 0.64 0.3911217138473822 0.2488782861526178\n",
-      "data_resize_all\\6.5_3fcd2983f990c95ac6b40e583405d178.jpg 0.65 1.035639550005766 -0.385639550005766\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "Input_dir='data_resize_all'\n",
     "#Input_dir='test_result'\n",
@@ -2580,20 +1876,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "plt.plot(res[:,3])\n",
     "plt.plot(res[:,4])\n",
@@ -2606,20 +1891,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "plt.plot(res[:,0])\n",
     "plt.plot(res[:,1])\n",
@@ -2632,20 +1906,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "plt.plot(stat_Abweichung)\n",
     "plt.title('Result')\n",
@@ -2657,20 +1920,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "plt.plot(stat_Anz)\n",
     "plt.title('Result')\n",
@@ -2689,27 +1941,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkIAAAHHCAYAAABTMjf2AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB/QElEQVR4nO3dd3gT9R8H8He6F20p3VBomQUpGyobmQWUKbKUIeACASv+AGWjggMFBUVQhoACKoKy90b2hpZZZksppYvSmfv9URqS5jJ7aZLm/XoeHtrL3eWT6+Xuc98pEwRBABEREZENsjN3AERERETmwkSIiIiIbBYTISIiIrJZTISIiIjIZjERIiIiIpvFRIiIiIhsFhMhIiIisllMhIiIiMhmMREiIiIim8VEiIhswrJlyyCTyRAXFyfZPuPi4iCTybBs2TLJ9klEJYuJEBGViMJEpPCfi4sLgoOD0alTJ3z33XdIT083d4ga/fbbb5g7d665wyAiE5BxrjEiKgnLli3D0KFDMWPGDISFhSE3NxcJCQnYu3cvduzYgYoVK+Kff/5BnTp1TPL++fn5yM3NhbOzM2QymUHbvvzyy7hw4YJaaZIgCMjOzoajoyPs7e0ljJaISoqDuQMgItvSuXNnNGrUSPH7xIkTsXv3brz88svo1q0bLl++DFdXV8nf197eXvJkpbBki4isF6vGiMjs2rZti8mTJ+PWrVtYuXKlYnlMTAxeffVV+Pj4wMXFBY0aNcI///yjeP3EiROQyWRYvny52j63bdsGmUyGjRs3AhBvI7RhwwZ07doVwcHBcHZ2RpUqVTBz5kzk5+cr1mnTpg02bdqEW7duKar1QkNDAWhuI7R79260bNkS7u7u8Pb2Rvfu3XH58mWVdaZNmwaZTIZr165hyJAh8Pb2hpeXF4YOHYrMzExjDyURGYiJEBFZhDfeeAMAsH37dgDAxYsX8eKLL+Ly5cuYMGEC5syZA3d3d/To0QN///03AKBRo0aoXLky1q5dq7a/NWvWoGzZsujUqZPG91y2bBk8PDwQHR2NefPmoWHDhpgyZQomTJigWOeTTz5BvXr14OvrixUrVmDFihVa2wvt3LkTnTp1QmJiIqZNm4bo6GgcPnwYzZs3F22o/dprryE9PR2zZs3Ca6+9hmXLlmH69On6HDIikoJARFQCli5dKgAQjh8/rnEdLy8voX79+oIgCEK7du2EiIgIISsrS/G6XC4XmjVrJlSrVk2xbOLEiYKjo6OQnJysWJadnS14e3sLb775ptr737x5U7EsMzNTLYa3335bcHNzU3nfrl27CpUqVVJb9+bNmwIAYenSpYpl9erVE/z9/YVHjx4plp09e1aws7MTBg0apFg2depUAYBKjIIgCD179hTKlSsndniIyARYIkREFsPDwwPp6elITk7G7t27FaUlSUlJSEpKwqNHj9CpUydcvXoV9+7dAwD07dsXubm5WLdunWI/27dvR0pKCvr27av1/ZTbIhW+T8uWLZGZmYmYmBiD44+Pj8eZM2cwZMgQ+Pj4KJbXqVMHHTp0wObNm9W2eeedd1R+b9myJR49eoS0tDSD35+IDMdEiIgsRkZGBsqUKYNr165BEARMnjwZfn5+Kv+mTp0KAEhMTAQA1K1bF+Hh4VizZo1iP2vWrIGvry/atm2r9f0uXryInj17wsvLC56envDz88Prr78OAEhNTTU4/lu3bgEAatSoofZazZo1kZSUhCdPnqgsr1ixosrvZcuWBQA8fvzY4PcnIsOx1xgRWYS7d+8iNTUVVatWhVwuBwCMGzdOYxufqlWrKn7u27cvPvvsMyQlJaFMmTL4559/0L9/fzg4aL7EpaSkoHXr1vD09MSMGTNQpUoVuLi44NSpUxg/frwiBlPT1JNN4MgmRCWCiRARWYQVK1YAADp16oTKlSsDABwdHdG+fXud2/bt2xfTp0/HX3/9hYCAAKSlpaFfv35at9m7dy8ePXqEdevWoVWrVorlN2/eVFtX33GHKlWqBACIjY1Vey0mJga+vr5wd3fXa19EVDJYNUZEZrd7927MnDkTYWFhGDhwIPz9/dGmTRv89NNPiI+PV1v/4cOHKr/XrFkTERERWLNmDdasWYOgoCCV5EZMYUmMcslLTk4OfvjhB7V13d3d9aoqCwoKQr169bB8+XKkpKQoll+4cAHbt29Hly5ddO6DiEoWS4SIqERt2bIFMTExyMvLw4MHD7B7927s2LEDlSpVwj///KMYoHDBggVo0aIFIiIiMGLECFSuXBkPHjzAkSNHcPfuXZw9e1Zlv3379sWUKVPg4uKCYcOGwc5O+3Nes2bNULZsWQwePBijR4+GTCbDihUrRKukGjZsiDVr1iA6OhqNGzeGh4cHXnnlFdH9fvXVV+jcuTOaNm2KYcOG4enTp/j+++/h5eWFadOmGXfQiMh0zNtpjYhsRWH39cJ/Tk5OQmBgoNChQwdh3rx5Qlpamto2169fFwYNGiQEBgYKjo6OQvny5YWXX35Z+PPPP9XWvXr1qmLfBw8e1Pj+yt3nDx06JLz44ouCq6urEBwcLPzvf/8Ttm3bJgAQ9uzZo1gvIyNDGDBggODt7S0AUHSlF+s+LwiCsHPnTqF58+aCq6ur4OnpKbzyyivCpUuXVNYp7D7/8OFDnXESkelwrjEiIiKyWWwjRERERDaLiRARERHZLCZCREREZLOYCBEREZHNYiJERERENouJEBEREdksDqiog1wux/3791GmTBm9h9knIiIi8xIEAenp6QgODtY6wCoTIR3u37+PkJAQc4dBRERERrhz5w4qVKig8XUmQjqUKVMGQMGB9PT0NHM0REREpI+0tDSEhIQo7uOaMBHSobA6zNPTk4kQERGRldHVrIWNpYmIiMhmMREiIiIim8VEiIiIiGwW2whJJD8/H7m5ueYOg4rByclJaxdLIiIqfZgIFZMgCEhISEBKSoq5Q6FisrOzQ1hYGJycnMwdChERlRAmQsVUmAT5+/vDzc2Ngy5aqcKBM+Pj41GxYkX+HYmIbAQToWLIz89XJEHlypUzdzhUTH5+frh//z7y8vLg6Oho7nCIiKgEsEFEMRS2CXJzczNzJCSFwiqx/Px8M0dCREQlhYmQBFiNUjrw70hEZHuYCBEREZHNYiJEJrV3717IZLJi96qTaj9ERETKmAjZqCFDhkAmk0Emk8HR0REBAQHo0KEDlixZArlcLtn7NGvWDPHx8fDy8tJ7mzZt2mDs2LHF3g8REZEuTIRsWFRUFOLj4xEXF4ctW7bgpZdewpgxY/Dyyy8jLy9PkvdwcnJCYGBgsdvfSLUfMq3svHzkywVzh0FEpDcmQjbM2dkZgYGBKF++PBo0aICPP/4YGzZswJYtW7Bs2TIAQEpKCoYPHw4/Pz94enqibdu2OHv2LADgypUrkMlkiImJUdnvt99+iypVqgBQr9J69OgR+vfvj/Lly8PNzQ0RERH4/fffFdsOGTIE+/btw7x58xQlVnFxcaJVY3/99RdeeOEFODs7IzQ0FHPmzFGJIzQ0FJ9//jnefPNNlClTBhUrVsSiRYskPopUKCs3H/Vn7ECnufvNHQoRkd6YCElIEARk5uSZ5Z8gSPMU3rZtW9StWxfr1q0DAPTp0weJiYnYsmULTp48iQYNGqBdu3ZITk5G9erV0ahRI6xatUplH6tWrcKAAQNE95+VlYWGDRti06ZNuHDhAt566y288cYbOHbsGABg3rx5aNq0KUaMGIH4+HjEx8cjJCREbT8nT57Ea6+9hn79+uH8+fOYNm0aJk+erEjgCs2ZMweNGjXC6dOn8d577+Hdd99FbGysBEeKirp4Pw2ZOfm4lphh7lCIiPTGARUl9DQ3H7WmbDPLe1+a0QluTtL8OcPDw3Hu3DkcPHgQx44dQ2JiIpydnQEAX3/9NdavX48///wTb731FgYOHIj58+dj5syZAApKiU6ePImVK1eK7rt8+fIYN26c4vf3338f27Ztw9q1a9GkSRN4eXnByckJbm5uCAwM1BjjN998g3bt2mHy5MkAgOrVq+PSpUv46quvMGTIEMV6Xbp0wXvvvQcAGD9+PL799lvs2bMHNWrUKNYxIiKi0oElQqRGEATIZDKcPXsWGRkZKFeuHDw8PBT/bt68ievXrwMA+vXrh7i4OPz3338ACkqDGjRogPDwcNF95+fnY+bMmYiIiICPjw88PDywbds23L5926AYL1++jObNm6ssa968Oa5evaoyIGKdOnUUP8tkMgQGBiIxMdGg9yIiotKLJUIScnW0x6UZncz23lK5fPkywsLCkJGRgaCgIOzdu1dtHW9vbwBAYGAg2rZti99++w0vvvgifvvtN7z77rsa9/3VV19h3rx5mDt3LiIiIuDu7o6xY8ciJydHsviVFZ0qQyaTSdorjoiIrJvVlQgtWLAAoaGhcHFxQWRkpKJtiS6rV6+GTCZDjx49TBabTCaDm5ODWf5J1Ztq9+7dOH/+PHr37o0GDRogISEBDg4OqFq1qso/X19fxTYDBw7EmjVrcOTIEdy4cQP9+vXTuP9Dhw6he/fueP3111G3bl1UrlwZV65cUVnHyclJ5zQXNWvWxKFDh9T2Xb16ddjbS5cUEhFR6WZVidCaNWsQHR2NqVOn4tSpU6hbty46deqks6ojLi4O48aNQ8uWLUsoUuuQnZ2NhIQE3Lt3D6dOncLnn3+O7t274+WXX8agQYPQvn17NG3aFD169MD27dsRFxeHw4cP45NPPsGJEycU++nVqxfS09Px7rvv4qWXXkJwcLDG96xWrRp27NiBw4cP4/Lly3j77bfx4MEDlXVCQ0Nx9OhRxMXFISkpSbQE58MPP8SuXbswc+ZMXLlyBcuXL8f8+fNV2h8RERHpYlWJ0DfffIMRI0Zg6NChqFWrFhYuXAg3NzcsWbJE4zb5+fkYOHAgpk+fjsqVK5dgtJZv69atCAoKQmhoKKKiorBnzx5899132LBhA+zt7SGTybB582a0atUKQ4cORfXq1dGvXz/cunULAQEBiv2UKVMGr7zyCs6ePYuBAwdqfc9JkyahQYMG6NSpE9q0aYPAwEC1Urpx48bB3t4etWrVgp+fn2j7oQYNGmDt2rVYvXo1ateujSlTpmDGjBkqDaWppHH8ICKyPjJBqn7XJpaTkwM3Nzf8+eefKjfOwYMHIyUlBRs2bBDdburUqTh37hz+/vtvDBkyBCkpKVi/fr3e75uWlgYvLy+kpqbC09NT5bWsrCzcvHkTYWFhcHFxMeZjkQXh37N4Tt5KRu8fjwAA4mZ3NXM0RGTrtN2/lVlNiVBSUhLy8/NVSiIAICAgAAkJCaLbHDx4EL/88gsWL16s9/tkZ2cjLS1N5R8Rkbmcuv0Ybb/eiz0x7O1IZApWkwgZKj09HW+88QYWL16s0rBXl1mzZsHLy0vxT2wwPyKikjL4l2O4kfQEQ5cdN3coRKWS1XSf9/X1hb29vVrD2gcPHogOvHf9+nXExcXhlVdeUSwrbHTr4OCA2NhYxTQQyiZOnIjo6GjF72lpaUyGiMhsnuRIM+8fEYmzmkTIyckJDRs2xK5duxRthORyOXbt2oVRo0aprR8eHo7z58+rLJs0aRLS09Mxb948jcmNs7OzYhRlIiIiKt2sJhECgOjoaAwePBiNGjVCkyZNMHfuXDx58gRDhw4FAAwaNAjly5fHrFmz4OLigtq1a6tsXzgIYNHlxWUl7c1JB/4diYhsj1UlQn379sXDhw8xZcoUJCQkoF69eti6dauiAfXt27dhZ1dyzZ4KRy3OzMyEq6trib0vmUbh6NYckJGIyHZYVSIEAKNGjRKtCgMgOhWEsqIzkxeXvb09vL29FQM6urm5STbCM5UsuVyOhw8fws3NDQ4OVve1ICIiI/GKX0yFDbU5kaf1s7OzQ8WKFZnMEhHZECZCxSSTyRAUFAR/f3/k5uaaOxwqBicnpxKtWiUiIvNjIiQRe3t7ti0hIiKyMnz8JSJJKHe6Yw88IrIWTISIiIjIZjERIiJJsI05EVkjJkJkEEEQsO7UXVxLzDB3KGTBWDNGRNaCjaXJIP+ei0f02rMAgLjZXc0cDRERUfGwRIgMcuZ2irlDIAul0ljafGEQERmEiRARERHZLCZCREREZLOYCBGR5DiOEBFZCyZCREQWjHPfEZkWEyEyiMBmsKQHniWm8+nGS2g3Zy8ysvPMHQpRqcBEiIjIivx88CauP3yC34/eNncoRKUCEyEikhybCElHU3urrNz8Eo6EqHRiIkREZIVy8uXmDoGoVGAiRERkhXLymAgRSYGJEBFJjo3qTS+biRCRJJgIERFZME3d51k1RiQNJkJEJAnlMiA2ljY9Vo0RSYOJEBGRFWIiRCQNJkJERFYoO0+9+/zVB+m4l/LUDNEQWS8HcwdARESGK1r9+DA9Gx2+3Q8AiJvd1QwREVknlggRkSQ4I5Z53Ux6Yu4QiKwSEyEikhwbSxORtWAiRERERDaLiRARSUKl+zwHVCQiK8FEiIjIwmiaaFXqbYiIiRARkUW58iAdjT/bheWH48wdCpFNYCJERJJj4YTxZvx7CUkZ2Zj6z0Vzh0JkE5gIERFZEDs7DkRAVJKYCBGR5FggZDxXR+Muy5omZyUi7ZgIERFZEDcnDvhPVJKYCBGR5NiDyXgujvbmDoHIpjARIiKyIK56JkJFU00mn0TGYSJERGRBnBx4WSYqSfzGEZHkWDZhPLZ5JipZTISIiIjIZjERIoOwGQJponxu8DwhImvBRIjIxmTn5Zs7BDIxNpwm0h8TISIbsicmETUmbcXPB26Y9o14HyYiK8FEiMiGfLD2DADg002XzRsImRQLhIj0x0SIiCTB3k5EZI2YCBGRJFQaS7NuzKx49In0x0SI9JYvFxCTkGbuMIhsCgvaiEyLiRDpbcqGC/jvRrK5wyArwDYq5sVeY0T6MyoRWrFiBZo3b47g4GDcunULADB37lxs2LBB0uDIsqw6etvcIRAREUnK4EToxx9/RHR0NLp06YKUlBTk5xeMSeLt7Y25c+dKHR8RkU0zpmyH5UFE+jM4Efr++++xePFifPLJJ7C3fz5LcqNGjXD+/HlJgyMi68Qbcel16X4aDl9LMncYRJJxMHSDmzdvon79+mrLnZ2d8eTJE0mCIiIi45myiVCX7w4AAA787yWE+LiZ7o2ISojBJUJhYWE4c+aM2vKtW7eiZs2aUsRERFaOjXVLv9vJmeYOgUgSBpcIRUdHY+TIkcjKyoIgCDh27Bh+//13zJo1Cz///LMpYiQishlFu8sb032e4zgR6c/gRGj48OFwdXXFpEmTkJmZiQEDBiA4OBjz5s1Dv379TBEjEVkZ3obNiwVyRPozOBECgIEDB2LgwIHIzMxERkYG/P39pY6LiKwMq8OIyBoZlQgVcnNzg5sbG8sRERGRdTI4EQoLC4NMy+yKN27cKFZARGSdlMuDWDgkDUNK2XjIiYxjcCI0duxYld9zc3Nx+vRpbN26FR999JFUcRER2TxBMHJAxRLIipjsUmlhcCI0ZswY0eULFizAiRMnih0QEVknzj6vnSAIuPv4KSqUddVaqk5EJUuySVc7d+6Mv/76S6rdERGVKov230DLL/dg1pYYvbcRYLnd55nLUWkhWSL0559/wsfHR6rdEZGVUbn5skBITWECtGi/adpRMi8hMo7BVWP169dXKdYVBAEJCQl4+PAhfvjhB0mDIyKyZcY2lmb7HSL9GZwI9ejRQ+V3Ozs7+Pn5oU2bNggPD5cqLiIim2fJ+QyTLSotDE6Epk6daoo4iMjasWbMYvD4E+lPr0QoLS1N7x16enoaHQwRET3HUhci09OrsbS3tzfKli2r9V/hOqa2YMEChIaGwsXFBZGRkTh27JjGdRcvXoyWLVsqYmzfvr3W9YnIeGyjYjlKYroT9hqj0kKvEqE9e/aYOg69rFmzBtHR0Vi4cCEiIyMxd+5cdOrUCbGxsaLzne3duxf9+/dHs2bN4OLigi+++AIdO3bExYsXUb58eTN8AiIi/VnaeEycT45KI70SodatW5s6Dr188803GDFiBIYOHQoAWLhwITZt2oQlS5ZgwoQJauuvWrVK5feff/4Zf/31F3bt2oVBgwaVSMxEtoIDKkrP2LzDVEefeRCVRkZPupqZmYnbt28jJydHZXmdOnWKHZSYnJwcnDx5EhMnTlQss7OzQ/v27XHkyBG99pGZmYnc3Fyt4x1lZ2cjOztb8bsh7aOIiKzdnyfvIj0rF0Obh6m9xupPKo0MToQePnyIoUOHYsuWLaKv5+fnFzsoMUlJScjPz0dAQIDK8oCAAMTE6DdS6/jx4xEcHIz27dtrXGfWrFmYPn16sWIlskUsBZKGvm1vtCUixUlSxv1xFgDQoVYAKpR1M35HRFbC4JGlx44di5SUFBw9ehSurq7YunUrli9fjmrVquGff/4xRYySmD17NlavXo2///4bLi4uGtebOHEiUlNTFf/u3LlTglESlQ4sLTAzCY5/Rnae+m75h6VSyOASod27d2PDhg1o1KgR7OzsUKlSJXTo0AGenp6YNWsWunbtaoo44evrC3t7ezx48EBl+YMHDxAYGKh126+//hqzZ8/Gzp07dVbdOTs7w9nZudjxEtka3iOlV9LHVFeio/wqe41RaWFwidCTJ08UPbTKli2Lhw8fAgAiIiJw6tQpaaNT4uTkhIYNG2LXrl2KZXK5HLt27ULTpk01bvfll19i5syZ2Lp1Kxo1amSy+IjoOeZE0jC2utHo7XRsxmSXSiODE6EaNWogNjYWAFC3bl389NNPuHfvHhYuXIigoCDJA1QWHR2NxYsXY/ny5bh8+TLeffddPHnyRNGLbNCgQSqNqb/44gtMnjwZS5YsQWhoKBISEpCQkICMjAyTxklki3iPtH66GkMrJ1hMiqi0MLhqbMyYMYiPjwdQMN1GVFQUVq1aBScnJyxbtkzq+FT07dsXDx8+xJQpU5CQkIB69eph69atigbUt2/fhp3d89zuxx9/RE5ODl599VWV/UydOhXTpk0zaaxERMVldPd5JilEejM4EXr99dcVPzds2BC3bt1CTEwMKlasCF9fX0mDEzNq1CiMGjVK9LW9e/eq/B4XF2fyeIiogHL7Ejaq1d8fJ+7AwV6GnvUrmDsUlb+bWBsg/lmpNDK4auzgwYMqv7u5uaFBgwYlkgQREZUmKZk5+OjPc/hgzVlk5aoPPWJs3lHS2xFZM4MTobZt2yIsLAwff/wxLl26ZIqYiMgKcbA9w2XmPE9+8uTmP2iGNJZmrzEqLQxOhO7fv48PP/wQ+/btQ+3atVGvXj189dVXuHv3riniIyKyWYIgGJVwGFs1qau3GRtLU2lkcCLk6+uLUaNG4dChQ7h+/Tr69OmD5cuXIzQ0FG3btjVFjERkDXhjlJyAkk042H2ebJHBiZCysLAwTJgwAbNnz0ZERAT27dsnVVxERGQkKfIVJj1kK4xOhA4dOoT33nsPQUFBGDBgAGrXro1NmzZJGRsRkU0zJBkpicSFuRGVRgZ3n584cSJWr16N+/fvo0OHDpg3bx66d+8ONzdOzkdky9h+xLykOP66q8b4h6XSx+BEaP/+/fjoo4/w2muvscs8EZFERJMMoWR7ZyknU6LjCJVcKEQlxuBE6NChQ6aIg4isnPJ93Ni5rmxZ4RGTQaa0zJC6MeUfOdcYkb6K1ViaiIikoU+SoXfVlLFVY8ZtRmTVmAgRkSRUSoR4RzWcWM2YcQVCxoegs0hIgjchsjBMhIiILEBhdZa2ai0TFwgZNPs8UWnBRIiIJMFbZPFoaCtdrO2liEHq95Dak+w8HLj6ELn5cnOHQlaKiRARSc4C75cWT7SxdJHMQ9txLYnhC3TtNjE9C/+cvY+cvJJLSoYtP443fjmG73ZdLbH3pNJFr15jZcuWhUzPPpzJycnFCoiIrBPHmCkeizh+xRxH6OXvDiIxPRvRHapjdLtqEgam2X83Cu45q4/fwYcda5TIe1LpolciNHfuXMXPjx49wqeffopOnTqhadOmAIAjR45g27ZtmDx5skmCJCLrYhE3dSsgiPysUrJTdH0tx1WK4Qt0jSOkS2J6NgBgx6UHJZYIERWXXonQ4MGDFT/37t0bM2bMwKhRoxTLRo8ejfnz52Pnzp344IMPpI+SiCweUx/DKSc2lpA7GtJpzNIaTpfguJNUyhjcRmjbtm2IiopSWx4VFYWdO3dKEhQRkS0QK8XRNgyB9jZCmrfTOx5dr1tW7qOiJEfgptLF4ESoXLly2LBhg9ryDRs2oFy5cpIERUTWR/WmTgazgO7qukqoOJ8clUYGT7Exffp0DB8+HHv37kVkZCQA4OjRo9i6dSsWL14seYBERKWVWPKotdRHy4sqSYyx8Riwgr492IgsncElQkOGDMGhQ4fg6emJdevWYd26dfD09MTBgwcxZMgQE4RIJe3CvVQMWnIMF+6lmjsUsiosLTCUzhKWEh5ZWmV/nImebITBJUIAEBkZiVWrVkkdC1mIPguP4GluPk7deowL0zuZOxyiUktXGyG19fVMd4xNUnT1PBPr5WYpZGwuTUYyakDF69evY9KkSRgwYAASExMBAFu2bMHFixclDY7M42luPgAgIzvPzJGQNVG991rabdIy6Z7SwsidGUlXoiVYciZEZCSDE6F9+/YhIiICR48exV9//YWMjAwAwNmzZzF16lTJAyQiKq3E2vVoqy7Te64xCRoJca4xshUGJ0ITJkzAp59+ih07dsDJyUmxvG3btvjvv/8kDY6IqDRTLREqXpIhRZJiSPd5KSaHlRK7z5OxDE6Ezp8/j549e6ot9/f3R1JSkiRBEdmC6w8z8DQn39xhSEaKcWxsjeiYQRKMEC1pPMqva1jXEjAPImMZnAh5e3sjPj5ebfnp06dRvnx5SYIiKu3+u/EI7ebsQ9fvDpg7FDIr7Q2SDdqTjiRGv2gE0Z91vR+RNTM4EerXrx/Gjx+PhIQEyGQyyOVyHDp0COPGjcOgQYNMESNRqbPhzH0AwI2kJ2aORDocUNFwOktgtLYRErS8Zqp4ij9WEZGlMTgR+vzzzxEeHo6QkBBkZGSgVq1aaNWqFZo1a4ZJkyaZIkYiEiEIAlKf5po7DKPk5Mk5Dk0Rz7vPSzEwomnaC6kmSpbWRoiVY2QcgxMhJycnLF68GDdu3MDGjRuxcuVKxMTEYMWKFbC3tzdFjFSKpD7NxYI913AnOdPcoVi9SesvoO707dh/5aG5QwGg//QLD9KyUHvqNkSvPVsCUVk2KdvcSJF7SNl4m8haGJwIzZgxA5mZmQgJCUGXLl3w2muvoVq1anj69ClmzJhhihipFPnk7/P4alssui84ZO5QrN6qo7cBAHN2XDFzJIZZdfQ2cvLl+Pv0PXOHYnaiU2xoKXXRf0BFY+PRv10Q0yQqLQxOhKZPn64YO0hZZmYmpk+fLklQVHoduf4IAJD8JMfMkZDU9L35sgLjOdVStGJ2n5egBMeQRIcFRlRaGJwICYIgWhd79uxZ+Pj4SBIUlV68dtoGDrynH12TrhoyoKLUgz7rHlBRSxshCd7/QVoWtl9MgFzOc4lMS++5xsqWLQuZTAaZTIbq1aurJEP5+fnIyMjAO++8Y5Igicjy6Xu7YpvW5/Tp8l4wh1bJJAO6pkmRoou+vtrN2YeM7Dx80TsCfRtXxMP0bJRzd4KdnfgJxPOKjKV3IjR37lwIgoA333wT06dPh5eXl+I1JycnhIaGomnTpiYJkoisC6tN9CNWwqJvqY/aa3r26NI3Hp0DKhr1DvornOtwd0wiAjxdMGTpcbxSNxjf969frP3ujU1EpXLuCPN1lyJMKgX0ToQGDx4MAAgLC0Pz5s3h4GDUxPVk49gTpfTS92/LWcKfM3QcIVPT1UbIHN9fuQD8sPc6AODfs/eLlQidvJWMIUuPAwDiZneVJD6yfga3EXry5Al27dqltnzbtm3YsmWLJEFR6cU0iFiFIU5s0tWiv2tPRKQd7LA4U2xImTDJ5YJeH0if8+rsndTiB0SljlGTrubnq8+PJAgCJkyYIElQVHqxQMg2aPs7Mw96TvfcXiU815jyz7q60pdQbHIJLxpMwkmMwYnQ1atXUatWLbXl4eHhuHbtmiRBERHZArG5vbQlR/q3ETIyHkPGESqhHC2fD09kYgYnQl5eXrhx44ba8mvXrsHdnY3PSDu2ESpQGp9MVduXaP47l8bPbiwpEwvJR5bWsUZJfZMFQZCs9ImnHokxOBHq3r07xo4di+vXryuWXbt2DR9++CG6desmaXBEpRXzQQJ0t7kRoNq4XP/zxsheYwY03i6phxp9q8bYCJ+MZXAi9OWXX8Ld3R3h4eEICwtDWFgYatasiXLlyuHrr782RYxUivD+X3rpO9cYJ8d8TnWCVUFtmWH7kiQitXjEXy05crl+n02f04rnHokxuA+8l5cXDh8+jB07duDs2bNwdXVFnTp10KpVK1PERyUsLUv/2cw1jTKufSMDAyplNpy5h1mbY+Bbxsmg7bZfTMDsrTH4rl991C7vpXsDsgo6S4QMaSSkY18Gb1eM76qUhUX5LD4lEzNqMCCZTIaOHTuiVatWcHZ2ZpZdiqRm6p8IKcvMyYObE8eW0mXM6jMAgIS0LIO2e2vFyYL/fz2BwxPbSR0WmcH9lKc4GfdY8Xvh/d7YXEQwov1OvlzA0GXHUSPAA590Ve0EIz6O0POff9hzHS8Ee6Gqv4cBURpO3yk29LkL8VZFYgyuGpPL5Zg5cybKly8PDw8P3Lx5EwAwefJk/PLLL5IHSJar8KK4cN911JqyDbtjHujexsQxlXaFo+0ay5T3Ab0nXeXNCADQbPZufLb5suJ3fRoES91l/fD1JOy/8hCLD9x8tn+l99LRnT/2QTraf7NP0njEyAXOXEemZXAi9Omnn2LZsmX48ssv4eT0vHi/du3a+PnnnyUNjqzD7C0xAIDxf503cySkiyXcUNioVZyiRMjInmTGbJeTJ9e8Dx1zjZUUKbvP88wjMQYnQr/++isWLVqEgQMHwt7eXrG8bt26iImJkTQ4smxFr0/l3HW3e2H3ef3l5svVlhlz9ARBwJ8n7+Jm0pPiB6X1fcR/LgmJ6VnYE5No1TOV6xO5sfOQ6R+D/uMIFWc/hhAEgdcNMimDE6F79+6hatWqasvlcjlyc41rX0KlQ1k3PRKhEoijNJj2z0WET96KGw8zVF8w4gD+fOAmxv1xFoOXHLOIJ2JTVI21m7MPQ5cdx/oz96TfeQkpvNmLTcRq8L703E6tLbaFjXQNFLRj0odebVVZL0siDE6EatWqhQMHDqgt//PPP1G/fvFmBSbziE99ij9P3lUrJtel6FOas6Pu04kPdvpZdjgO+XIBC/ZcV1luzOFbefQWAOB2cqZJb2PK470U94ZpaAlAelZB26k9sQ+L9b7mpKtxsqZ1nq9b/L+urklXzUHPqcaIjGZwN58pU6Zg8ODBuHfvHuRyOdatW4fY2Fj8+uuv2LhxoyliJBOLmnsAqU9zce/xU/SsX97o/djzaUtyahNwGnGzyyuhOQr0fnLX8fqxm8kY8esJTH2lFno1qGBQDNZchSLWRqi4+9K5ntrvymNBWUYbISl7jSkzavgPKpWMGln633//xc6dO+Hu7o4pU6bg8uXL+Pfff9GhQwdTxEgmlvq0oEpzT2yiQU/yRde0s9N9UWH/j+IRO3q6jrrytd6Ul/08vaswnv8sdrMd8esJpD7NRfTas1KFZiV0D2Bo6kRPyhKhvHw5zt9N1TtB1kTKSVdV92uS3ZIVMmrgl5YtW2LHjh1Sx0JmJkD/p3oxeuRBZCgtbTgk2J2k8pQadxfG+SAtC19ti8UbL1ZC3RBvAKq9xvLlAhzsbe/EOXX7sdoysXGEjGXMeaLP4I16lzQJwCd/X8CaE3fwTusqGNu+GvLkAjycDb/lCPq+r4GnkVwQYG8RrebI3IweAe/EiRO4fLlgDIxatWqhYcOGkgVFZiIIxXpKsjOymPnkrWTsv5KEkS9VhZODwYWUFu/3Y7fxJDsPw1tWNnhbKW6KJVX6L1Yi9L8/z2HflYf48+RdxM3uqva62PlWnHit5SF/3s6rassMbSOkraGzvpSTn6J/C/EpNvR/kzUn7gAoGGds9fHbSMnMxaUZnQweeFXKUjDlUytfLsDRXuOqZEMMToTu3r2L/v3749ChQ/D29gYApKSkoFmzZli9ejUqVDCsTp+eS0jNgkwGBHi6SL7vtKxcuDs5wF5LsU3Bk5cBVWNFVtWrakxk971/PAIA8HZzxNDmYXq/vzWQywVMXFcwvlLniCDDtxcEXLyfqvj9aW4+Up/mwsvV0ah4TJkTKZcmFv509UG6egxKQYhVexibUFsTsY8oOo6QAYnH5vPxRm1XSC4IRg2BcODqQ7Ss5qd1nZRnI9ZfeZCBes9KBgvl5stx4OpDNA71QRkX8fPaFAmuFTcnsziCIOB43GPUCCgDLzfjrk3mZPDj9/Dhw5Gbm4vLly8jOTkZycnJuHz5MuRyOYYPH26KGG1Cdl4+Xpy1C5Gf7xIdP8YQsQnp2HHp+SjP91Oeos607ej142Gd2xo6r49y4qTPDUzb3uNMPM6NOSgfT2OmL9lw5j66fndQZdlHfxjWdkZl9nKDI9Cfvm2ElImdbmJn0fm7qSoJoeYdGhyCWYh9xuffJc0fQlMbnpiENGy/pHtkd23y5YJR4wi98csxHL6epLJMU7seseXf7riCN5edwAdrzugdq7GUL1HmmsMsKzcf0WvPYOO5+2Z5f1PYeC4er/10BF2/f96j/PGTHGy9kFDs+1lJMDgR2rdvH3788UfUqFFDsaxGjRr4/vvvsX//fkmDsyWPnzy/SWbm5Bu9n03n4tFp7n6M+PUETj9rh7DpXMGT4tk7KVq3FYSCmZ71JUBQKQXQq6mHlmvP8iO3sO1igv4BoKBdyv/+PIs/T941aLuSonzhzzPk4Gph6A2vxKrGRHqn6brViN0Yi/bkycjOwyvzD6Lrdwet4qJaVFJGNpYfjlNZJvbQoE/VmCY3H6o+RBjTa2zerqt6jCMk7oTSnGkAcP2h+EONWInzD3sLhojYeTlRW6g6GXqam6oRti6rjt7GulP3MOq302Z5f1MovMfcffxUsey1n47gnZUn8ePe65o2sxgGJ0IhISGiAyfm5+cjODhYkqBskRS9qQ5eTcLI304pfr9wr+AJWt8vvADB4IuDcimAFFUab684iYNXk3Sv+Mw/Z+9j7Ym7GGdgKUlJUc59ckuoG7uyf8/ex61HmYrfTVs1ptxYWvNnPXL9keJn8UTo+c+Hryeh07fPH7AMHevKEoz49QSm/nNRZZnYV+Xws+OiffRo8e7tYqVxKZk5OmNbtP+G4ucf914XHcpREARk5earvacyfc8ro9oxGbuhCJXSUYlOpc3n43EtUb0KWJNHGdnSvLGFu5pYMBjsv2ctv+TL4EToq6++wvvvv48TJ04olp04cQJjxozB119/LWlwtkT5OqbPuBl5+XJsOR+PxPTns5hvvhCvsk72s5uGvlUWgmDYU5IgqO5bnzE59En4Xv/lqN4xPMrQfbE3J+Xi9zwzlGa8/7vqU6fy0Z+64YKi1FAKuXqeZ7tinj/5ixWSKTc1G7D4KO6lPH/KLFqdcTwuGeP/PGdYoBJ6mJ6NdafuKhIFMadvp+i1r+92XVUMZVFI369j0e/tb8duo96MHVislOiIOXlL9e+vnOgU/vzBmjOImLYN8alPNV5LZDJoPQaKfepcw3iGjglkaNVYYloW1p++p5KMH7yahPdWnUL7b/SvDdHWTrM0MlfJmyEMToSGDBmCM2fOIDIyEs7OznB2dkZkZCROnTqFN998Ez4+Pop/pD/l5EefL+iyw3F4d9UpdJn3vP1IbpGn5ew8OfbEJOKrbbEa96M8m3lBImRI1Ko3d/tnZ1Pq01wcvp5UIvM+KR+r34/dxt7Y4hWvGyozJw/j/jiLXZfFq6vWHL+j+DkxXfxJ8HhcMrZeMKxKUArLj9xCzx/E242dvZOiPr2HBiv/u4Xms3erNIwWAOy/8hDxqVmaN4SGEiEt5QtFq9/6LDyi6J1U8L7i59y9lKcqN/n0rFy8uew41p8u3pQcvX48hOi1ZzFXpBeYNpq+4vdTnmL1cS2fR0MboaLDXvx29DYAqMxun5Wbj2M3k7Um5GIlQuvP3EduvoD5u6+hz8Ijott9vf0Kwidv1bjfQrquCelZ4u3oTHElMeQGvSc2EU0+34Wxa85g4b7nVT1Fh0EQO7Zn76QgPvV5Mm8pnQEu3U9DbIL+JVmJ6Vl4beER/H1avRmCto9kBXmQ4b3G5s6da4IwSLntgz5j+ex8duNNUipmffREtXQkN1+OocuOa9yHIAiImLZNZVnRi8PBq0kI8XFFpXLuGuJWKhF6dgN745ejOHc3FbN7RaBCWTdEVPBS9HJS7/JrRO8WuQCZrOAJUPlYFfbOOjulo149F1YdvYXbjzIxpn010S69mTl5uHg/DQ0rllXpEXfpfhqGLT+O6A7VcetRJv48eVete/iemERMWn9BpTSjaOlMocKby4H/vYQQHzedcQPGdynW5xL8IC0L3RccAgDEze6K5Cc5WPXfLfRsUB7f7riK6gEeeLt1FcX6k9ZfAACVz9pLQ4JVlHivMc3r62pntfVCAhbvv4ERrZ4PVRA6YRMA4J3WVTChcziAgnYpu2MSsTsmET3ql8ffp+/i+13X8NMbDVEtoIxesQPAneSCz7z9YoJi31m5+Vh/+h461w7SeB5qugl/s+OK3u+tvAttpb6JaVnw93TBuD/OYuO5eIxuWxXRHWtoXF9s/0BB25bi0vWQFzFtOxYPaoQOtQIM3rc+57bycTfkQW3o0ufX0d0xiRjdrhoA1WO04r9b+GzTJfz6ZiTqV/TGnO1X4FfGGTM3XgIAxfXBEkqEMnPy0OW7gobNVz7trHXYkifZebjzOBNLDt7EsbhkHItLRs/6+vcOV/6bf7DmDJKf5GDZ0MYWNaq3wYnQ4MGDTRGHzVNOKDQlQjEJaZiy/iKiO1YXfarYHaNaGqKrPcXsrTEqX+QbSRlqF4fCaiqxMWCKxioXBOTmy3HubkHbpAnPEpNq/h7YMKo5lh2OU7tga2o3k56ViwnrzsPTxQGdawchMycfUbUDAQDRa89g75WH2BndWvRiVnfGdsTN7orsvHzsi32IF6uUg6dIt9xP/i64gf+0/wbeblUZE7vUVHn9vVWnsDf2Ib7oHYG+jSsqln/4x1nEp2bhoz/PoUtEoGL5yv9uYfaWGDSoVBb7rxg+59XDjGy9E6EDBrSjUiZ2tHPz5XC0f34hLFpdMmXDBWw8F485SjfpES0r6zVcgtr7F7kRit0YtV0gdU0XIhcKSkGaV/VFrWBPPFEq8Vy477oiWSnaTuODNQVtzKb/ewkrh0dq/xAibiQ9wfDlxzGhc038e/Y+5u26iiWHbmL7B601ximmaDWavnONabupN/l8F+Jmd8XGZw1afz54U2MipPp+0j/KD1h8FBvfb4Ha5b0gCAI2n1cvCZ264YJqIiQSRmZOHvov+g9tavhrfC+5XMCxuGTULu+lGMhR+fz7enssbjx8gpXDI+GiZUChoqU8DnYyPM3Jx4yNl3BFqRR08rMHgjGrT6NH/fIqJUeF0rJyMX/3NY3vVVIK5+YDCo6lk4P4hNmPn+Sg/kz1wZMPX09COXdnRK89g+gO1dVGi1f+Dt9/9oCUly/H389KYK8/fIKq/h5SfBRJGFw1tmzZMtHleXl5mDhxYnHjsVn6lAi9s+IkjsUlo9+i/9SKIsXq5zUlQhvP3cf+Kw/x0z7V9gNZuXKDZu8WBNW45QLw/S71KoKriRmYu/MqvtyqXkWXlSferiBi2nZsOheP34/dwaAlx/DOypNITMtCRnYe1p+5j5TMXOyOSdR4QxEEAfN2XsVbK05i+PITaq9nF3nfn561pTh56zG+2BqD7Lx87H02gecfJ1SLgpWPtXIPv0nrLyAjO8+oJAgAHO30/zoeui6eCF1LTMeK/24Z1B6psF3KibhkjFx1Cu+tet7g/outMYobqLKjN5Nx8GqSQY2XkzKy1drAZOeqb6/tMCh/N1Yf01xC8fhZQ2FNbcg0nTcHryXh7uPnjcuzcvNx6X6aXiVwOy8nYsSvJxQPJFceZGj8O2jam6eL/s+mKlVjBpQQujkV3PTFkiflY2qqKo3CXo97YhNVOncUEkuwCx+uCv1x4i7O3k3FPJHrTaFfj8Sh36L/MOjZw1x2Xr7K93Xtibs4cesx1p++hw1n7uHms+E7Np67j7GrT+PGwwxM//civizStMDOToaf9l/H78duqz00AEB8apZoT6mzd1JQZ9p25JiwreCNhxno+cMh7I7R3rNU+Qhr+w4XbXdaaMDio+g0dz8u3k/DsOUnVKqzwyZuxmebLil+z80X0G/REUXjaaDkerLqy+ASodGjR2PTpk1YtGgRypYtCwCIjY3FgAED8OjRI8yaNUvyIG2BcklJl3kHsPCNhmhe1ReJ6Vl4b+UpxKdmqVQ9KJcICYKAxp/t1Ot9dl56oLXb5sr/xG8umm4Eh649vyHLBQFLDsWJrrdIpNHmiv9uYbsB3eWbfL5L5ff/aWkkeyk+TdEt99jNZGTm5KlUf91W6klVKCs3H72fjbW08r9biuVyQUD02jNoWc0XPetXULkZPy3GUAdF7bj8ABEVvHQ2cAWglsQWKmy0OXn9Bdyc1UXtdbHrz/4rD9GrQQW8KtL+Q1PX1/6L/wMAtKmhfSA9ZY0+VT9Hs3Lzse1iAkb/fhqO9nYY3KyS1jYUH6w5g6jagXicmYMFezR3yx3481HEze6KhyI9dDafj1fpubblvOrFfubGS/jpjUa4dD9NUX3QsVYAOr0QiK51grSWHtx69ARRtQNx/lmPzXdWnhRdT9P3yVnHUMeakhNDpsZJyshRVBcW9YfSMBR/nrxr1CCguqRm5kAQBLy5TP0BBVCvOrpRZHyxj/8+r2gDpazoaVPY1urU7RTkywU0+nSnSklIobUn7uDUs5K4g+NfUlwf158R7+107GYyKulZcqvsew0lQTl5cny9PRaL9t/AJ11qItTXHdUDPDQ2R1CWnZePpYfi8NO+61g5PBKT1l/A6dspeHPZCY2l+IBqx4aD15Jw7m4q3mtTBT7uTnB4Vjp8P+WpotTcUIsP3FT5/b8byeg87/kYQ5Y2QbfBidDp06fx+uuvIyIiAkuXLsWVK1fwv//9Dz169MAPP/xgihhLrcPXk5CQmoVeDSqolKykZ+cpLuSfb7qMEyJPHcpFj/lyQfQLLnZpHP6r+MVHl8af7RJdXlj9BRR01/VydVRpgK1NYVGyKfT76T+V34cvP4HlbzZRVAHN2HhJbZvPNj1vWKp8PE/dTsGp2ylYd+oezt5Jxe3k50nU0ZvJksX83a6reDHMR6WBa3EUfYoGxEtCoteeFT3H9FFYamasp7n5eHtFQbKQnSfHgj3XEeDprHH9E7ce6x3r1QfpisS20J3kTJUSLwB4t8jvyc/a2hUmQUBBKcb2Sw+w5UI8Fg9qBJlMJtrQ1N5OplLqpWlsHE1Vm/libaA03DPkcgFyuQA7O5nKOGRi1p0yfJytXTGm6XiQKxeQJnK9KvT4SQ5+PqD5YUAsCRKj3B4oJTNH9BoJQJEEAQUdF/RhTINnsYbgcrmA73ZdVTwoKn/3z07tiPm7r6JH/fJ4IdgLQMG1/n7KU7y94iScHOxw7m6K4jtddODVojJz8pCVK4ePu5NKx5rCyY2XPRvrqneDCviid4TGJF7MpvPiJUeaFD74b7uYgGM3k/Fxl5pmbTtlcNVYlSpVcOjQIfTq1QtRUVH44IMP8PPPP2PVqlXw8vIyRYwqFixYgNDQULi4uCAyMhLHjh3Tuv4ff/yB8PBwuLi4ICIiAps3bzZ5jPoasPgooteeRUxCmuhAcQv2XMMdpQGqlCmfM4VP50X9cvCm6HJjJIk8WV8oMtLvntiHRk/9ILX0IsnY4euPMHb1GcXvj0XGWPlbjx5Ey4oMjCe1AT/rP3RAofSsXLWqPgD4dqd6w1tNVTX63lykduFemtqyB2nSjLPS4Vv1Ls0P0rT3YgOAsm7i7SWAgsQmbOLmgvGN5qrvXyaTIUukuk9fRdvMCQLgrNR+69aj56UjB68loccPhyCXC3iQrv1zFd7sDPX4ifTDU/x29Db+UOrpV1RaVh4+3VT8hwHlUrIsPatw9R3ry5hR1MUemgYtOYb5e8RLij7deAmLD9xUSXBGrjqFll/uwaX4NJy5k6K1l+/e2ESceJbY5eXL0fKLPWgwcweSn+Ro7XTw16m7qPrJFtEHKakUTgfz9oqT+OXgTbOPsm3UDJebNm3C6tWr0bRpU3h7e+OXX37B/fum/yBr1qxBdHQ0pk6dilOnTqFu3bro1KkTEhPFn1wOHz6M/v37Y9iwYTh9+jR69OiBHj164MIF05VEGOPe46eijUC/2haLtKfiT3rKTyTH44x7mi+uvj+pV6U4O1rupKnKTy0R5dWTdn1LsizN9YdP0PKLPSrTqgDipTVPJKzKk8LHf5/XvZKEpBrRYcBi8YTVTqbe2NwQyu2TgILu88rfqb6LVB96zt1Nxcnbj3HeRDctTW3RikuKRKco5XYqeflylb91pp7fbbEHPjGX4tUTeGMcvKb5+Bbtmg8AWw1oSjBk6XFFdXfvhUcUvYobzNxh0LhHpvDNjisqzRMeahhapKQYfNd6++230adPH4wfPx4HDhzAuXPn4OTkhIiICKxdu9YUMSp88803GDFiBIYOHYpatWph4cKFcHNzw5IlS0TXnzdvHqKiovDRRx+hZs2amDlzJho0aID58+ebNE59KLcR+O/GI9ESCkC1S7IyC+iBKXpTMaStgjn8fuw2Xv/5KH4/pvmJ1BolpmdjhJHVnrbkiYmT3eKUBgHiJRLODtrbDfVZeETRJklq1jQNROyDdMjlAv46WVCicVOpbZG+DzliHTrEXJYoEdJGeZqSE3HJSNSjNFNMZk6ezumVzCFB6fNo675fEgxuI3To0CEcPXoUdevWBQAEBgZi8+bNWLBgAd5880289tprkgcJADk5OTh58qRKzzQ7Ozu0b98eR46ID/J15MgRREdHqyzr1KkT1q9fr/F9srOzkZ39PDtNSzPNCa+cMBRtWKZM07xjlppvmDuz12XiupItgSDLok9pzeWENJXBIc1JEAAXCy5ltTRT/rkg2uFDrLOGNRHryKCvvj+JN50wt4zs57Udf5++h0FNQ80Wi8HfsJMnTyqSIGUjR47EyZP6N64yVFJSEvLz8xEQoDrQVkBAABISxIsLExISDFofAGbNmgUvLy/Fv5CQkOIHL8KYOmZlRccMshS6RhImMidN7TGU3Ul+Ktq+yBx+OXhT4wSmpE5Tr9ctZhi53VKYqrSwuH5Q6vWp7zQ0pmJwIuTs7Izr169j0qRJ6N+/v6J9zpYtW5CXZ51tLJRNnDgRqampin937pimCkWKUVqJLMG3fdUfjEga/1jBhJWl2ct1pB8+gAqYcjwlQxmcCO3btw8RERE4evQo1q1bh4yMgkGSzp49i6lTp0oeYCFfX1/Y29vjwQPVBqEPHjxAYGCg6DaBgYEGrQ8UJHqenp4q/0xhpkj3bTKN+hW9zR1CqdazfgVsfL+FucMgJf2bVNS9ksTqVDB9r+GSZmiX7roh3qYJpBTSNUp8STI4EZowYQI+/fRT7NixA05Oz7uZtm3bFv/9Z7q6SCcnJzRs2BC7dj0fz0Yul2PXrl1o2rSp6DZNmzZVWR8AduzYoXH9kiIIAkLLGT4gFxmnnLuzwY3L/ctoHstGk8961jZ4m5IwrmN1/C9K99xShqpQ1hVbx7YEANQu7wWHZwd594fi00q4O2lv9KvJ9c+74N02VXSvaMEc7Uu2d0OIj6vR2w6IrIhpr9QSfa1wjq124epTWzSoWNbo97RUGzQMqjipa02EB6rPSefnoXrdKOPsgIpGDL5oC4oOZXHBjFV4BidC58+fR8+ePdWW+/v7IynJNF0tC0VHR2Px4sVYvnw5Ll++jHfffRdPnjzB0KFDAQCDBg1SaUw9ZswYbN26FXPmzEFMTAymTZuGEydOYNSoUSaNUxeZTIY+jUzT9ojEGdokK9jb8BtJSqb2Qe3MJSdfwNutpE8kRr5UFeGBz0tMj3/SHjujW6OynwfeUpr0tFDhPF+G+LxnBOztZBinxyShmpTVYwJeU9r4fgtEhpUr0fdsVe35iN8tq/ni6z76VV9uHt0Sn/eMQIcXxEvNoztUx+UZURjaPEzttTY1/DDqpaqY1LWmyJbW4+U6QRjTrhq2jW0FPw0PRMNbVhYtBa1U5AH37NSOGNS0kknitHZFJwlPNsGYVfoyOBHy9vZGfLz6KJKnT59G+fLlJQlKk759++Lrr7/GlClTUK9ePZw5cwZbt25VNIi+ffu2SmzNmjXDb7/9hkWLFqFu3br4888/sX79etSubf4n95J+QtSkrciTHQA4l1B3xsLJELX5613NJXgNilR7lTcigRGjPODY9g9a4cMO1dXW+eOdpmhZzVfxu6m7ZhurvLcL7O1kWkds1mbr2JZ440X1i3mvBqrf97LuToqJFMdHqSc9UbW1t7eY3StC5feudYIwILKgisfYUWer+Xvg1OQORm0rZv9HLxm8Te3yXvikBJKDt1tXxvI3m2Dz6JaorTROlr2dDK82rCA65UpRhcdZ7Hv048AGAABXJ3vRuaLsZDKM61QDb2i58S8e1EhnDJo0rVwyyaSDnQwfdKiOGoFlsEpkAt7fni1zsLfDsqGNseiNhpje7QUMaRaKt1s/fwBwtJfBzk6GrkrtjHw9tH8HX22o/6zu5lbO3Um0VMxYxozWLdl7G7pBv379MH78eCQkJEAmk0Eul+PQoUMYN24cBg0aZIoYVYwaNQq3bt1CdnY2jh49isjI5yfq3r171SaF7dOnD2JjY5GdnY0LFy6gSxfdF4OSoDzbty6uReYf0nWz3zCyueLn99tWxT+jmqu8Xk+pHltTvf62sa1QRo8kRVm1ZzfBP99pKlp0XtSiNxpi9Vsv6lyvYSUfja81rVIO3/Wvr/j9/bZV9YhUt9y850VI1QPKYGgL9SfgxqE+WDEsEmPaVUOwlwsGNwuV5L2Lq2g7hd4NCi6uVfw0z/ZcI0D8gta/SQjCAz0xs0dtnJ3SESNahuHXN5vgxuddtI5vY28nw+JBjfBRpxpYP7I5Tk/uoPHpGgBGvlQF/ZpUxHDl4yxBE4IfBjaATCbTK+HWR4iPq1GNw2sGeeLU5A7oVjdYkjiGi5yPMsjQurofagWrtmssvMHI9LjRiOWbVf09EDe7q8q8Y9p2pe288NZSOhfs5aI1Njcjq1YNpTwWVPWAMtj+QSuV16sozZrepoY/Or4QiMHNQjGt2wvwL+OiKPn8bUTBtS3I6/n1WtefoOh52jhU/+rGd9tUKVaiaajVb72IrWNb6V5RT+acfszgROjzzz9HeHg4QkJCkJGRgVq1aqFVq1Zo1qwZJk2aZIoYS6WQsur1xkWfsAvZ28kUbYpWDY/EhiKJTVHKN0I7mUwxT02hJmE+GB8VjlpBnhii4ebt4+Gk9T7Uurr6ZJt/j2yO7R+0QqNQH/zwegPF8p81fDnLeTihdnmvYk3LkScX4OH8/ALpKnqxNPyOWvSm7eHsgMkvi7eb+KBDdRya0BYBntov5CVlpFJ7GuVJFGf3qqPxRrztg1YqVUiFyfcbL4Yqlnm5OeKTrrXQqrqf6AzhRXWoFYCRL1VFvRBvlHVXn7Zi2dDGip8Lb57llJ6Yizs45/FP2qPaswRPqgHbZDKZQQ8xyu/r4+6E+FTxAVINVaGsKwKLnG9ZueJjjin/pV7SMUmuPn/Xgn2qr6d8I9s8uqXodsrJTNHvWDkdpSXaJruVUqiv6mSn1Ys8JOg6Qu+0roK42V3ROFT9AU7X4b2aqDp+VXSHGvjy1TroUS8Yl2Z0QhU/zROxvtumCjrUCsBEkSroMi7SPAgoM+R7oA+rSoScnJywePFi3LhxAxs3bsTKlSsRExODFStWwN6+ZE7U0qBdTX+MblcNiwc1wvqRzTGrV4Tiyb0oOxmwcXRLbB7dEs2r+uosXlXdVib65Xu3TRVsHtMS3m5OODGpvVqRv7ODncqTT6FJXWsibnZXLB3SWGX5/AH14eHsoLhoODvYY+P7LbDw9YZoreHiW/ikmlNkHiBDBpBrVMlH5QtZzl3/Y6MpCQSAWb0i0LxqOSx/s4li2QAtPXH0edrWpIyzA8p7u6J+RW/UlaDnjaPSzddJ6dhULOeGef3qadwuTOkGcHhCW2wd21KtdEFKytU3hX9DQSlptS9G9XGwl4vKjVaKa2xhuycnA24AnkVuQDnF6ClTtCR41YhIlcRW0+jJyqfmkiGN0bq6n8bSXn2rJ3Stpum8qRXkqWg8/MPA5w9L5dyd4COSLKu+qV6hFdsoXaXKxYhDLIFUFuj5/G88pl01vFjZB681CsHcfvXh5uSAXR+2wdmpHbFkiPrDpaNdwXn5dusqiJkZhfY1n4+h90XvOnrHOEXDA19RDs++n0uHNta7Z+4LwZ7oGiFeRa7r2JiS0WliSEiIyQYbtAUymQzRSu1O6oV447CGeX3s7QqK9vW5Kb3TWrVRrJ1M/SZdtATG18MZKJLzONnbYX7/+vhyWyyGtwhD9wWHADx/ilN+clwxrAlaVlNPdmqX91K52SnrEhGoqKJTnjD0u/710bl2IDJz8vHx3+fRs556KVmdCl4Y3bYa8gUB7Wv6q8yppfNiqkR5mpNCLar6omudIIT4uGHVcNVqO1cne/h6OCEpw/hGfWPaVcO8XVdVljk62OHA/16CnZ0McrmA+6lPEeTlijy5HDUmbdW6v6ufdcbm8/G4+iBDMVigt9Lft2jbGuVz4YveEbj6IAOdIwoaxs55rR4mr7+A916qgrLuTqKlOFJSbodWGJbyn6Tok+3rL1bUOGBe3QpeOKs031b5sqpJw4zutTHyt1NFN1Mzr189jFGanLfQsqGN0aZGQXWvg44E7Z3WVbBwX8FgcUWrOpSTfns7Gd5vWxVzd6qeD2LeblUZ3eoFKybglMlkqOLnge/611eMNSQ2u3lRMpkMy99sgpO3ktH7R/XRivVtiiW2mj43MplMhv3/ewmCIKici03CfDTODl9Synu74u+RzXRWoxpzw+7fpCJ+P3Yb0R2r439/ntO4Xr8mIej4QgCeZOehl4YHYy9XR9QOVr+uKp+XLo72Ku1QO9cOxLRXaiE9Kw9zdqhPxlw0hhl6DO9S+PDyUg1/vFTDH6ETNgEoaNu36Zz4bPRfvVoX/RaJj5JtzmmjOHa7BdH0BRNrKKr8NFUobnZXtZ45YkXduhq4VQ/wgEwmQ4iPG77vXx91Q7wxs/sLeKVuMDqLNHjV1L5E2c+DGqFf4xCsfbspVg6LxA8DGyouhMo1IN3qBsPR3g5ero5YMKAB2tdSHRm8RVVf/DOqBdrXCkCnFwIhk8lUpiFxd9a/VFLs6Xzl8EitY7AYUhonRuyJu1vdYMXfyc5Ohgpl3WBvJ4Ozg73a09nC1xuq/O5ob4fu9cqjolJvFeUY7bR8w18I9sKkl2sp2mCF+bpj5fBINKviq3kjCSlXG4kVs1coUn08qWst/DK4kWij7xFFeqkVfQLuWidI9ElXeRiLV+oGo7tI4g2oJpDaZqcHgHylhvaVi7TLylFK+i/N6ISx7dUb4QMFJawHx7+Eqv4emNS1JiZ2qanWVrAoQ3o6airB1LdESN8qNH3fXyYzzTyFF6Z30nvdndGt4V9Gd/W2MYW/n/WojQP/ewmvNQpRaaNZlKujPTq9EKgxCSrkXORcmPxyLbXvkPJ9QyaTYUjzMDQSqa5T9tuISLg5aU4E94xro/hZU9VYkKcL/h0lPq6YvZ1M4wN9cc+p4pC+4pCMpuk8ELs4dYkIQstqvjhwtaAUSVMX4ZpBqklKeGAZjT3FfhsRicvx6Xizeajaa280DcUbReaCOf5Je2Rk58Ffj7Yx7WsFqCU1hbxcHZH6VL+u58q9uQq9oPTFMqR3UW6+HAfHv4QWX+zRe5v5A+pjwl/nFeOp6PJF7wgcuJqEjc+ekIpeO4Y0C9VaRfdmizAMbR6KDWfu4+zdFHTUcAyVb5LlPJ7fqMWS60VvNMS9lKcaS+tKinIVkz5teFwc7dGuZgBcRZ5WHZQyvhXDmqglIADgL5JA/fN+CyzYcw0X76Vp7fatfFrVC/HG5JdroZq/BwYtOVYkDhkGNQ1F0yrlsPRQHD7vqdoTTnlSVU2NiuuFeOPlOgVVXjujxcdkUrb27ab4+/Q9jG0nnlSJ0fQt0b+NkMiyYt7HdCVCxuzekEby+vaUNaZ3k51dwYMlUPD9m7P9CtacUJ+1QFdpYyHl5gPf96+PV0Ta/n3UqQb2XXmo0n1f0NJeskFFbzTRkSgplzJpu9ZGVPDCv6Na4JX5B1WW29vJ8GXvumj1lfo115z9qJkIWRBNF6ERLdXHZAFUv5C7Pmyj8tq/o1rgUnwqXqqhmvQsHtRI49Ngsyq+BpUG+JVx1toTSF8rhjXB9H8v4eMumseZCQ8sg5iEdNEn9lBfd2wa3QK+Hs4Qqe3SqE0NP7VSB12q+pfBn+8203v9vo0rom/jith4rqDYWPnY28mAad1e0LkPmUyGHvXLo0f9gs/es355/H36Htootb1qG+6Pl+sEoUZAGZUnOrFTqqOGMWJKmvKxcC5sI6THH7Bb3WB8t/saqgd4oH+TivBydVS5KGu6QBeO5ePsYIcuEUHoXi8Yni6OmNhZNQHa+H4LvPy96gVc+bsmk8kwrEUY8kSmCDg/rRNcnewR4uOGtuHqSWuujmkFvFwd8dWr4u05ZCoxPF/eJMwHTcK038C07UuZ3lVjJrhrfdy1Jno8q4IXI3ZmtKruh/1XHoq88rwa39vNUesYX7s/bA17O1mxkkBD+Hu64LOetUUTIXs9D6zyQ4SmBLJSOXecntxB0VkCgNZ+IyuHR6quK0K5WYWuxFEu8l22t5OplF4rK047y+JiImRBNJ0Gw0S6ygKqF6OibWMiKnghQqnh7cb3WyAlM1fxVGJJ6lTwxl86kou17zTF5ftpoj0xACh6xiWm6T/pq6ZGe1IRexpVLrnR9Fl0+axnbbwU7q+SCLk7O2D+APXqUnOOzWEIR4eCOPVJZEe1rYZawZ6IDCunaMe0R2kSYk03E78yzjj+SXu4O9trLf4XKykT26PYTUO81+JzRTsGAMAnXWris82XMaFzON5qWdkEVQQiPbw0rKnvjdiQfeqrXog3YmZGIXyy9nZxymZ0ewFtvt6rtryynzuWDSno6LDnwza4kfQEckFAnyKzuL/VqrJo6aE2UnylNCUc+pZoKycN2ibwLvo+ymt6ODvglbpB+P1YQUKmz7WijIsjlg5tDBk09+Ir3I1yk4VC2s4vc16qjEqEsrKycO7cOSQmJkJepKqiW7dukgRmi8Qy4trlPSW5MJq7GqS4PF0cEanHgGpiE/lpurma+glEefyR99tWxb3HT1WSn+8H1BfbTCc3Jwe9x6OxkjxIkcjqU6Dn5GCnNjij8ndEW/WCsSWYUp0r/ZqEYMGe62he9fm5PKJVZXSvH6xX+xRFPJJEI7JfiXqNGcvQLvKhvu6oF+KNM3dSVJb/PKiRouShrLsTGmpo+P9xF/0Gupz6Si1M/7egSlaq3k2HJrTFk+w87I1NxOebYwCoVvHqK1+kuYAmytfC01M64LtduhvqAwVjBtV8Nop80VoGTRqJjIFU+PHCfN1xM+mJ6mvWVCK0detWDBo0SHQ6DZlMhvx88bEsSDexfEfbE7KV3ONKVJCXK6r5e8DJwQ4X76eZNRblxqsfPpsiQhAEvFwnCOXLuhp04zOWsSMym8rbrSvjp303MPKlgt6NO6NbIzEtSzHsgiFVm8oclD6nKS6omg7jwtcb4OcDN3Hi1mPRsbWKGtu+OpqElUOjSqo3Cb0a6eoVqX40HSK9SyT0XiidXJHSNACiiZChpTy6qDQMluhzFg6H8FSp5MSIPAhhvvp/1sL2lPZ26uNhaTon5g+ojxeNGNXb0d4OTSuXw5EbjxTLCs8vsYb/VtVG6P3330efPn0wZcoUxdQWJA2xp7ExWhrlmrNO1VLZ28mwZUxL2MlkqPzxZo3raRocsbhmdn8Bkzdc1Dhej0wmE63CMhVzjs0hZnyncPRpGKIYGK6qv4diWo7iUE5+TJH8afquRdUOQlTtINxJzkSQjpGRgYKbgz4Jk6lpOi/EH8bUs1Op+3cpx/PNa3URvfas2jrZeXJsG9sKAxb/pzJPlVgpsClJfXopn6+GlAhtGNkc1xIzDGofVtbdCcc/aa+owlX+KJrOicKG+/pS/q4ULZ3VVjVmVVNsPHjwANHR0UyCTED5C1be2xXHPmmntWGrZd3iLIeDvZ3O6sQuEaZpMPxG01DcnNVFYzfskmZpubKdnQxV/T00JhbGTqOgb28WY+naZYiPm86GpsWlcsiK+YfVtLm+D1diJXdSJd29GlTA2rfV5xfMys1HjcAyeLWRatdyTSVFpiL1A6jy7gw5d+uGeKO3EXOT+ZVxFm2/aIprRdHOINquy1Y1svSrr76KvXv3miAUUr6QzHmtbolUndgCTRNEmu79LCf7sJbG0oUGvlgRL1b2MXgGc+W2JSVZIlTaiB078c8u/Zg/ypqE+aj1nsvSkPAULRHqoyU5+OY1w+eJK8qUZ4I5q7JN8c5V/Dyw76M2it8LS4TETimraiw9f/589OnTBwcOHEBERAQcHVXHrxk9erRkwdka5RNBnxuYjVybTcLaEgRjGdPmwJzcnByw+i310gDd2z1PhBzMUCJkbTSd/vpWjZWEJ0WmDKnzrMNH0ZIn5Z54S4c21jpLfa8GFfD97mtqDXUNIfWlQ/nwmjMRkuqaWHQvKp/PXnPvUKtqLP37779j+/btcHFxwd69e4uMbSFjIlQMqmOV6LNFKbs6lyCx603LaiUzonJJGNu+GubuvIrpeoxTVBood1s3xQXVEkqElBOA4kajuY1QMarGJD5ErWv4A896ao1uVw3DW4YBADq9EICF+67D/1kPQOWxmfTp0VTcxE7qdneWkgiZ6hRXPtqlpvv8J598gunTp2PChAmws7bHTQunWiJk2PpkGLELTgcNozZbo7Htq+PdNlU0jl5c2ij3QjFF+YXtlAjpVzUm+TEWiSfM1x2HJ7SFj7uTStVn/YplsTO6FQK9CnpdZZd4GyFp96c88KApSjP1ZapkXznx1JboWVVj6ZycHPTt25dJkAmongh6VI2ZLpRSRfzpVf3oFZ3d29rZShIEqLYR0jV6szEsrSq1uOEUt2pMvLG09IK9XUXHFqrqX0bR4LewZ622OQKlJHnVmNLPJV4iZIrzWssutX2PrKr7/ODBg7FmzRp8/PHHpojHphlaIkTGUz6+K4Y1wYV7aRrnYCPLpzzcvzmfqk3J2HuWaMPUYlaNiU2fYC6NQn1wflpHg+YVM5Typ5W+akypxMTCEm4pKI9XpO2raVVTbOTn5+PLL7/Etm3bUKdOHbXG0t98841kwdka5ZNEn5PC0gbLsybKF/yW1fzQspr5x3Yh48lkMnzUqQYS07JQRYLB9Po0rIA/Tt5V/G5JN34paCwR0rvXmNg+Db8eta/pj52XEzFUy8TD+ijjIj7ptJji/iVNWSJU0jOwl8S7hfi44Y0XK8HDxUHrEBPmvJ0ZnAidP38e9evXBwBcuHBB5TVLaFBozYpOyKnLhM7hOB6XjKHNw0wYVenEU7X0GflSVcn2NbNHbTSv6ouxa85Itk8pFbdUwpCt9a0a0yVYZMDJRW80wuPMHJTzKP7kzfoyJnbDGi0Yxly98gDTtKcTOzdn9qiteztrKhHas2ePKeIg6DfKp7JK5dxx/JP2TEA1iCjvhfP3UvFqwwrYpTQpJ2B5bT7Isrg42qs0ni9lBULFfhAQRG6hmvb5+osV4eXqiH6N1dvw2NnJSjQJkoLU146qfmUk3Z8UvutfH6N/P23UuEti54Y+rKpESNnduwVFxxUqGD66JakzvPs8S+G0+eOdpriZ9AThgaoXmnfbVDF4ckeyPcpVz6UsD0LRcg0nezu81aqy/pvrcUB8PZyRlJGNfo0rWv2kz8qkvuR6uTni6Mft4GKGzg2aPkq3usGIeiEQTg4l1ynKnNMBGfwp5XI5ZsyYAS8vL1SqVAmVKlWCt7c3Zs6cqTYTPRlG+QvG/Kb4XBztUTPIUyVZLOPigPFR4WaMiqyF8oOJJbQRMuX14as+dTCuUw291xc7GkVD2vdRG+z+sLXFJUHGllgUMsXDZ4CnC7zc9G/nVBKMTYKMTWisbhyhX375BbNnz0bz5s0BAAcPHsS0adOQlZWFzz77TPIgbYWdShshZkKmwKNK+lIpETJ/HmQ0sXO+6OXFFDd3d2cHyWeBNxcr/vNbDatKhJYvX46ff/4Z3bp1UyyrU6cOypcvj/fee4+JUDGwRMj0WJVI+lJts2D+W6GU525x92TNiSE9Z4rLYb0Qb6O2s6opNpKTkxEerl61EB4ejuTkZEmCslUylgiZTO8GFfDXqbt4v610PYuodFP+Plrajb/YU2wU8/oS5K3eA4yXLOsj5Xm968PWuHg/DZ1eMG6EfqsaWbpu3bqYP3++2vL58+ejbt3iz+xry1TGETJfGKXSl6/Wwc7oVhjWgkMNkOEsLA8qtqLXF0OvN1X8PPDDwAb4oH11qUIqMcXtPk/iqvh5oFvdYKOTbKuqGvvyyy/RtWtX7Ny5E02bFswSfeTIEdy5cwebN2+WPEBbotprjF89KdnbyVDV3/K6qRLpS2V4DRNNsWGILhFBOOyapLzX4u+USpS5bjNNwnxwKT7NImIBjCgRat26Na5cuYKePXsiJSUFKSkp6NWrF2JjY9GyZUtTxGgzpLzQEVHxdY0IwgvBnqhvZLsHS1W0Z4/R1xsrvE4NjKwEAGhauZyZI7Fd/4uqgYmdw7FsaGPFMnN2nzeoRCg3NxdRUVFYuHAhG0WbANsIEVmWBQMbQBCEUldCa5K5Nq3kEL3VqjIaVPRGRAX9u/WXtqpRc3NzcsDbrasgLumJYpnVDKjo6OiIc+fOmSoWmydjGyEii2MpSZDq9UHamMz5NF7S7O1kiGRpEADL+rub83tmcNXY66+/jl9++cUUsdg8lgIRUUmQ6lKjfCPl1cv6FHdwSSlZTYkQAOTl5WHJkiXYuXMnGjZsCHd3d5XXOfu88TiZPBFpIuWIvUWfvvkMRuZmVZOuXrhwAQ0aNAAAXLlyReU1SylCtlaWVExJRBasuL3GpImiyCCwpff6VVo/mSXdcyy++/y5c+dQu3Zt2NnZcfZ5E5IpVVRaToElEZU2alNsmCcMq8HrselZ/ICK9evXR1JSwXgRlStXxqNHj0walK3ixYiINJGyM4VUJQG8ZpFUzHku6ZUIeXt74+bNmwCAuLg4zjJvIioDKpoxDiKyLVI8jPOaZX3MXZupXNJm8XON9e7dG61bt0ZQUBBkMhkaNWoEe3t70XVv3LghaYC2RPlEYFEsEZmKZL3GzH0npWKxpDn0LL6N0KJFi9CrVy9cu3YNo0ePxogRI1CmDKcrkBqvKUSkierI88W7WKhvXfyLD69fZK307jUWFRUFADh58iTGjBnDRIiIyFoxaSFYVvJq8SVCypYuXWqKOAiWdVISkYWR8PpgyFxj2mpPTDnaNZV+Hs7PUxCLbyNEJcNe6URwdxJvg0VEZMgtI8zXQ3175ixkAfzKOOPL3nXg7GgHR3uDJ7qQDBMhC+Jgb4c5feriaW4+/D1dzB0OEVmxtW83xZYL8Rjdrqraa0XzIG15kb6vMbmyPpbwJ3utcYi5Q2AiZGl6N6xg7hCIyAIZWvXUJMwHTcJ8xPdlQNZiQR2LSGL82xYwX1kUEREZpbilL6aYYoPIWhlVInT16lXs2bMHiYmJaoMrTpkyRZLAiIjoOSmTDrUpNrTsnLlO6cW/bQGDE6HFixfj3Xffha+vLwIDA1W+QDKZjIkQEZGJFb9ESKqqMeXrv9HhEJmVwYnQp59+is8++wzjx483RTxERGRqTFoITF4LGdxG6PHjx+jTp48pYiEiIg2kvGdJN8WGNPuxdBXKupo7BDIhgxOhPn36YPv27aaIhYiIrFRpHlCxTXU/TOgcjhXDmpg7FEnZ2ZXev5khDK4aq1q1KiZPnoz//vsPERERcHR0VHl99OjRkgVHRETqijtZJm9/hpHJZHindRVzhyG5gZGVsPrYHUTVDjR3KGZlcCK0aNEieHh4YN++fdi3b5/KazKZjIkQEZEJSDnTe9F9CUZmVhxQ0bp5uTpi30dtJD23rJHBidDNmzdNEQcREenJUsYRIutn60kQUMwBFQVBMPpJgoiI9Kd8uyp21ZhkjaXZfZ6sn1GJ0K+//oqIiAi4urrC1dUVderUwYoVK6SOjYiITKA0N2wmMpTBVWPffPMNJk+ejFGjRqF58+YAgIMHD+Kdd95BUlISPvjgA8mDJCKi54pdNSZViZDKz0yuyDoZnAh9//33+PHHHzFo0CDFsm7duuGFF17AtGnTmAgREZkAq56ITMPgqrH4+Hg0a9ZMbXmzZs0QHx8vSVBERGQ6phhQkYkaWSuDE6GqVati7dq1asvXrFmDatWqSRIUERFpVvxxhJi1EBUyuGps+vTp6Nu3L/bv369oI3To0CHs2rVLNEEiIqLikzJ5YekN0XMGlwj17t0bR48eha+vL9avX4/169fD19cXx44dQ8+ePU0RIxERKbGUcYSUkzPmVmStDC4RAoCGDRti5cqVUsdCRESaKGUaxR9HiGkLUSG9EqG0tDR4enoqftamcD0iIrJMkpUIsbE0lQJ6JUJly5ZFfHw8/P394e3tLfo0IQgCZDIZ8vPzJQ+SiIieY9JBJB29EqHdu3fDx8cHALBnzx6TBkREROqkTH5Mk0gxOyPrpFci1Lp1a8XPYWFhCAkJEZ29+M6dO9JGR0REkmMbIaLnDO41FhYWhocPH6otT05ORlhYmCRBiUlOTsbAgQPh6ekJb29vDBs2DBkZGVrXf//991GjRg24urqiYsWKGD16NFJTU00WIxGRqUg56apU2EaISgODE6HCtkBFZWRkwMXFRZKgxAwcOBAXL17Ejh07sHHjRuzfvx9vvfWWxvXv37+P+/fv4+uvv8aFCxewbNkybN26FcOGDTNZjEREpY6FJF1EpqJ39/no6GgABUWqkydPhpubm+K1/Px8HD16FPXq1ZM8QAC4fPkytm7diuPHj6NRo0YACuY869KlC77++msEBwerbVO7dm389ddfit+rVKmCzz77DK+//jry8vLg4GDUyAFERGZniaUvFhgSkV70zgZOnz4NoKBE6Pz583ByclK85uTkhLp162LcuHHSRwjgyJEj8Pb2ViRBANC+fXvY2dnh6NGjeg/kmJqaCk9PT61JUHZ2NrKzsxW/6xougIioJCiXxJdo1ZiWDIdTdVBpoHciVNhbbOjQoZg3b16JjheUkJAAf39/lWUODg7w8fFBQkKCXvtISkrCzJkztVanAcCsWbMwffp0o2MlIipV9Ey62ACbrJXBbYSWLl0qWRI0YcIEyGQyrf9iYmKK/T5paWno2rUratWqhWnTpmldd+LEiUhNTVX8Y084IrI0lpJzWEocRMVhVEOZEydOYO3atbh9+zZycnJUXlu3bp3e+/nwww8xZMgQretUrlwZgYGBSExMVFmel5eH5ORkBAYGat0+PT0dUVFRKFOmDP7++284OjpqXd/Z2RnOzs56xU9EVFLM1muMyQ6VcgYnQqtXr8agQYPQqVMnbN++HR07dsSVK1fw4MEDgydd9fPzg5+fn871mjZtipSUFJw8eRINGzYEUDDIo1wuR2RkpMbt0tLS0KlTJzg7O+Off/4xaa82IqJSSUvSpdJ93vSREJmEwVVjn3/+Ob799lv8+++/cHJywrx58xATE4PXXnsNFStWNEWMqFmzJqKiojBixAgcO3YMhw4dwqhRo9CvXz9Fj7F79+4hPDwcx44dA1CQBHXs2BFPnjzBL7/8grS0NCQkJCAhIYHTgBCR1WE1FJFpGJwIXb9+HV27dgVQ0FvsyZMnkMlk+OCDD7Bo0SLJAyy0atUqhIeHo127dujSpQtatGih8n65ubmIjY1FZmYmAODUqVM4evQozp8/j6pVqyIoKEjxj+1+iIj0pGevMSZqZK0MrhorW7Ys0tPTAQDly5fHhQsXEBERgZSUFEUSYgo+Pj747bffNL4eGhoKQanivE2bNiq/ExGVFiWadPAySqWcwYlQq1atsGPHDkRERKBPnz4YM2YMdu/ejR07dqBdu3amiJGIyOYpl75Y4jMexxQia2VwIjR//nxkZWUBAD755BM4Ojri8OHD6N27NyZNmiR5gEREZJlYHUalgcGJkI+Pj+JnOzs7TJgwQdKAiIhIO0tMQCwxJiJ96JUIpaWlKQZR1DXlREmOOE1EZCuUEw1LqRpj7kOlgV6JUNmyZREfHw9/f394e3uLDqVeOCs9u6YTERGRtdArEdq9e7eiSmz37t2cU4aIiFgdRqWCXolQ69atFT+3adPGVLEQEZEZWEhNG5FZGDygYrVq1TBt2jRcvXrVFPEQEZEOllMSwwEVyfoZnAi999572LRpE8LDw9G4cWPMmzcPCQkJpoiNiIiescTG0kSlgcGJ0AcffIDjx4/j8uXL6NKlCxYsWICQkBB07NgRv/76qyliJCIiC8e2o2StDE6EClWvXh3Tp0/HlStXcODAATx8+BBDhw6VMjYiInrGEuf1spQ4iIrD4AEVlR07dgy//fYb1qxZg7S0NPTp00equIiISANLrBpjTkTWyuBE6MqVK1i1ahV+//133Lx5E23btsUXX3yBXr16wcPDwxQxEhGRBWLyQ6WBwYlQYSPpkSNHol+/fggICDBFXEREpMTSq6EsPT4iTQxOhGJjY1GtWjVTxEJERFaEDaSpNDBqHKGUlBT8/PPPmDhxIpKTkwEAp06dwr179yQPkIiILJ+MFWVkpQwuETp37hzatWsHb29vxMXFYcSIEfDx8cG6detw+/ZtdqEnIjKBkk4zXBztkJUrR5MwH43rMPWh0sCocYSGDh2Kq1evwsXFRbG8S5cu2L9/v6TBERGReWwb2woTOodj0su1zB0KkUkZXCJ04sQJLFq0SG15+fLlOcI0EZGJKLfHKYmmOZXKueOd1lX0Xp/NhchaGVwi5OzsjLS0NLXlV65cgZ+fnyRBERGRZpYyjhCTHyoNDE6EunXrhhkzZiA3NxdAwVPK7du3MX78ePTu3VvyAImIyPIxJyJrZXAiNGfOHGRkZMDf3x9Pnz5F69atUbVqVZQpUwafffaZKWIkIrJ5lphosKcYlQYGtxHy8vLCjh07cPDgQZw7dw4ZGRlo0KAB2rdvb4r4iIjIGjAnIitl9FxjLVq0QIsWLaSMhYiIrAjbCFFpYFAiJJfLsWzZMqxbtw5xcXGQyWQICwvDq6++ijfeeIOjjBIRmYilX15ZTUbWSu82QoIgoFu3bhg+fDju3buHiIgIvPDCC7h16xaGDBmCnj17mjJOIiIiIsnpXSK0bNky7N+/H7t27cJLL72k8tru3bvRo0cP/Prrrxg0aJDkQRIR2bqSHkfIUJYYE5E+9C4R+v333/Hxxx+rJUEA0LZtW0yYMAGrVq2SNDgiIlIn9ThCljIuEZE56J0InTt3DlFRURpf79y5M86ePStJUEREZPmUS4FYIETWSu9EKDk5GQEBARpfDwgIwOPHjyUJioiIiKgk6J0I5efnw8FBc5Mie3t75OXlSRIUERERUUnQu7G0IAgYMmQInJ2dRV/Pzs6WLCgiIrIuHD6FrJXeidDgwYN1rsMeY0RERGRN9E6Eli5daso4iIjIirE8iKyVwZOuEhEREZUWTISIiKjY2ESIrBUTISIiIrJZTISIiKjYOOkqWSsmQkRERGSzmAgREVHxsUCIrBQTISIiIrJZTISIiIjIZjERIiKiYmP3ebJWTISIiIjIZjERIiKiYmOBEFkrJkJERERks5gIERFRscnYSIisFBMhIiIb16aGn7lDIDIbJkJERDasRVVfuDjaF3s/LA8ia8VEiIjIhrFGi2wdEyEiIio2JlRkrZgIERERkc1iIkREZMMEwdwREJkXEyEiIio2JlRkrZgIERERkc1iIkREZMMESFOUw8bSZK2YCBEREZHNYiJERGTD2LaHbB0TISIiIrJZTISIiGwYS4TI1jERIiIiIpvFRIiIyIZJ1WuMyFoxESIismHFqRqzY595KgUczB0AERFZpyAvF3SsFQAXR3u4OfF2QtbJakqEkpOTMXDgQHh6esLb2xvDhg1DRkaGXtsKgoDOnTtDJpNh/fr1pg2UiMiKFKdiTCaTYdGgRviuf33J4iEqaVaTCA0cOBAXL17Ejh07sHHjRuzfvx9vvfWWXtvOnTsXMhbhEhERURFWUZZ5+fJlbN26FcePH0ejRo0AAN9//z26dOmCr7/+GsHBwRq3PXPmDObMmYMTJ04gKCiopEImIrIObCtNNs4qSoSOHDkCb29vRRIEAO3bt4ednR2OHj2qcbvMzEwMGDAACxYsQGBgoF7vlZ2djbS0NJV/REREVDpZRSKUkJAAf39/lWUODg7w8fFBQkKCxu0++OADNGvWDN27d9f7vWbNmgUvLy/Fv5CQEKPjJiIiIstm1kRowoQJkMlkWv/FxMQYte9//vkHu3fvxty5cw3abuLEiUhNTVX8u3PnjlHvT0RkDTiOENk6s7YR+vDDDzFkyBCt61SuXBmBgYFITExUWZ6Xl4fk5GSNVV67d+/G9evX4e3trbK8d+/eaNmyJfbu3Su6nbOzM5ydnfX9CEREVqljrQBsv/QAw1tWNncoRGZl1kTIz88Pfn5+Otdr2rQpUlJScPLkSTRs2BBAQaIjl8sRGRkpus2ECRMwfPhwlWURERH49ttv8corrxQ/eCIiK/bj6w3xIC0Lwd6u5g6FyKysotdYzZo1ERUVhREjRmDhwoXIzc3FqFGj0K9fP0WPsXv37qFdu3b49ddf0aRJEwQGBoqWFlWsWBFhYWEl/RGIiCyKvZ2MSRARrKSxNACsWrUK4eHhaNeuHbp06YIWLVpg0aJFitdzc3MRGxuLzMxMM0ZJRERE1sQqSoQAwMfHB7/99pvG10NDQyHomDRH1+tERERkW6ymRIiIiIhIakyEiIiIyGYxESIiIiKbxUSIiIiIbBYTISIiIrJZTISIiIjIZjERIiIiIpvFRIiIiIhsFhMhIiIisllMhIiIiMhmMREiIiIim8VEiIiIiGwWEyEiIiKyWUyEiIiIyGYxESIiIiKbxUSIiIiIbBYTISIiIrJZTISIiIjIZjERIiKyMvZ2MnOHQFRqMBEiIrISbzYPQ0R5L0TVDjR3KESlhoO5AyAiIv1MeaWWuUMgKnVYIkREREQ2i4kQERER2SwmQkRERGSzmAgRERGRzWIiRERERDaLiRARERHZLCZCREREZLOYCBEREZHNYiJERERENouJEBEREdksJkJERERks5gIERERkc1iIkREREQ2i4kQERER2SwHcwdg6QRBAACkpaWZORIiIiLSV+F9u/A+rgkTIR3S09MBACEhIWaOhIiIiAyVnp4OLy8vja/LBF2pko2Ty+W4f/8+ypQpA5lMJtl+09LSEBISgjt37sDT01Oy/VoTHgMeA4DHAOAxAHgMbP3zA9IfA0EQkJ6ejuDgYNjZaW4JxBIhHezs7FChQgWT7d/T09NmT/pCPAY8BgCPAcBjAPAY2PrnB6Q9BtpKggqxsTQRERHZLCZCREREZLOYCJmJs7Mzpk6dCmdnZ3OHYjY8BjwGAI8BwGMA8BjY+ucHzHcM2FiaiIiIbBZLhIiIiMhmMREiIiIim8VEiIiIiGwWEyEiIiKyWUyEzGTBggUIDQ2Fi4sLIiMjcezYMXOHJIlZs2ahcePGKFOmDPz9/dGjRw/ExsaqrNOmTRvIZDKVf++8847KOrdv30bXrl3h5uYGf39/fPTRR8jLyyvJj2K0adOmqX2+8PBwxetZWVkYOXIkypUrBw8PD/Tu3RsPHjxQ2Yc1f34ACA0NVTsGMpkMI0eOBFA6z4H9+/fjlVdeQXBwMGQyGdavX6/yuiAImDJlCoKCguDq6or27dvj6tWrKuskJydj4MCB8PT0hLe3N4YNG4aMjAyVdc6dO4eWLVvCxcUFISEh+PLLL0390fSm7Rjk5uZi/PjxiIiIgLu7O4KDgzFo0CDcv39fZR9i587s2bNV1rHUY6DrHBgyZIjaZ4uKilJZpzSfAwBErwsymQxfffWVYp0SPwcEKnGrV68WnJychCVLlggXL14URowYIXh7ewsPHjwwd2jF1qlTJ2Hp0qXChQsXhDNnzghdunQRKlasKGRkZCjWad26tTBixAghPj5e8S81NVXxel5enlC7dm2hffv2wunTp4XNmzcLvr6+wsSJE83xkQw2depU4YUXXlD5fA8fPlS8/s477wghISHCrl27hBMnTggvvvii0KxZM8Xr1v75BUEQEhMTVT7/jh07BADCnj17BEEonefA5s2bhU8++URYt26dAED4+++/VV6fPXu24OXlJaxfv144e/as0K1bNyEsLEx4+vSpYp2oqCihbt26wn///SccOHBAqFq1qtC/f3/F66mpqUJAQIAwcOBA4cKFC8Lvv/8uuLq6Cj/99FNJfUyttB2DlJQUoX379sKaNWuEmJgY4ciRI0KTJk2Ehg0bquyjUqVKwowZM1TODeXrhyUfA13nwODBg4WoqCiVz5acnKyyTmk+BwRBUPns8fHxwpIlSwSZTCZcv35dsU5JnwNMhMygSZMmwsiRIxW/5+fnC8HBwcKsWbPMGJVpJCYmCgCEffv2KZa1bt1aGDNmjMZtNm/eLNjZ2QkJCQmKZT/++KPg6ekpZGdnmzJcSUydOlWoW7eu6GspKSmCo6Oj8McffyiWXb58WQAgHDlyRBAE6//8YsaMGSNUqVJFkMvlgiCU/nOg6A1ALpcLgYGBwldffaVYlpKSIjg7Owu///67IAiCcOnSJQGAcPz4ccU6W7ZsEWQymXDv3j1BEAThhx9+EMqWLatyDMaPHy/UqFHDxJ/IcGI3waKOHTsmABBu3bqlWFapUiXh22+/1biNtRwDTYlQ9+7dNW5ji+dA9+7dhbZt26osK+lzgFVjJSwnJwcnT55E+/btFcvs7OzQvn17HDlyxIyRmUZqaioAwMfHR2X5qlWr4Ovri9q1a2PixInIzMxUvHbkyBFEREQgICBAsaxTp05IS0vDxYsXSybwYrp69SqCg4NRuXJlDBw4ELdv3wYAnDx5Erm5uSp///DwcFSsWFHx9y8Nn19ZTk4OVq5ciTfffFNl4uLSfg4ou3nzJhISElT+7l5eXoiMjFT5u3t7e6NRo0aKddq3bw87OzscPXpUsU6rVq3g5OSkWKdTp06IjY3F48ePS+jTSCc1NRUymQze3t4qy2fPno1y5cqhfv36+Oqrr1SqRK39GOzduxf+/v6oUaMG3n33XTx69Ejxmq2dAw8ePMCmTZswbNgwtddK8hzgpKslLCkpCfn5+SoXeAAICAhATEyMmaIyDblcjrFjx6J58+aoXbu2YvmAAQNQqVIlBAcH49y5cxg/fjxiY2Oxbt06AEBCQoLo8Sl8zdJFRkZi2bJlqFGjBuLj4zF9+nS0bNkSFy5cQEJCApycnNQu/AEBAYrPZu2fv6j169cjJSUFQ4YMUSwr7edAUYUxi30m5b+7v7+/yusODg7w8fFRWScsLExtH4WvlS1b1iTxm0JWVhbGjx+P/v37q0ywOXr0aDRo0AA+Pj44fPgwJk6ciPj4eHzzzTcArPsYREVFoVevXggLC8P169fx8ccfo3Pnzjhy5Ajs7e1t7hxYvnw5ypQpg169eqksL+lzgIkQmczIkSNx4cIFHDx4UGX5W2+9pfg5IiICQUFBaNeuHa5fv44qVaqUdJiS69y5s+LnOnXqIDIyEpUqVcLatWvh6upqxsjM45dffkHnzp0RHBysWFbazwHSLjc3F6+99hoEQcCPP/6o8lp0dLTi5zp16sDJyQlvv/02Zs2aZfXTT/Tr10/xc0REBOrUqYMqVapg7969aNeunRkjM48lS5Zg4MCBcHFxUVle0ucAq8ZKmK+vL+zt7dV6CT148ACBgYFmikp6o0aNwsaNG7Fnzx5UqFBB67qRkZEAgGvXrgEAAgMDRY9P4WvWxtvbG9WrV8e1a9cQGBiInJwcpKSkqKyj/PcvTZ//1q1b2LlzJ4YPH651vdJ+DhTGrO17HxgYiMTERJXX8/LykJycXKrOjcIk6NatW9ixY4dKaZCYyMhI5OXlIS4uDkDpOAaFKleuDF9fX5Xz3hbOAQA4cOAAYmNjdV4bANOfA0yESpiTkxMaNmyIXbt2KZbJ5XLs2rULTZs2NWNk0hAEAaNGjcLff/+N3bt3qxVfijlz5gwAICgoCADQtGlTnD9/XuWCUHjBrFWrlkniNqWMjAxcv34dQUFBaNiwIRwdHVX+/rGxsbh9+7bi71+aPv/SpUvh7++Prl27al2vtJ8DYWFhCAwMVPm7p6Wl4ejRoyp/95SUFJw8eVKxzu7duyGXyxWJYtOmTbF//37k5uYq1tmxYwdq1KhhFVUihUnQ1atXsXPnTpQrV07nNmfOnIGdnZ2iysjaj4Gyu3fv4tGjRyrnfWk/Bwr98ssvaNiwIerWratzXZOfA0Y1saZiWb16teDs7CwsW7ZMuHTpkvDWW28J3t7eKj1krNW7774reHl5CXv37lXp+piZmSkIgiBcu3ZNmDFjhnDixAnh5s2bwoYNG4TKlSsLrVq1UuyjsOt0x44dhTNnzghbt24V/Pz8LLrrtLIPP/xQ2Lt3r3Dz5k3h0KFDQvv27QVfX18hMTFREISC7vMVK1YUdu/eLZw4cUJo2rSp0LRpU8X21v75C+Xn5wsVK1YUxo8fr7K8tJ4D6enpwunTp4XTp08LAIRvvvlGOH36tKJH1OzZswVvb29hw4YNwrlz54Tu3buLdp+vX7++cPToUeHgwYNCtWrVVLpOp6SkCAEBAcIbb7whXLhwQVi9erXg5uZmMV2ntR2DnJwcoVu3bkKFChWEM2fOqFwfCnv/HD58WPj222+FM2fOCNevXxdWrlwp+Pn5CYMGDVK8hyUfA22fPz09XRg3bpxw5MgR4ebNm8LOnTuFBg0aCNWqVROysrIU+yjN50Ch1NRUwc3NTfjxxx/VtjfHOcBEyEy+//57oWLFioKTk5PQpEkT4b///jN3SJIAIPpv6dKlgiAIwu3bt4VWrVoJPj4+grOzs1C1alXho48+UhlDRhAEIS4uTujcubPg6uoq+Pr6Ch9++KGQm5trhk9kuL59+wpBQUGCk5OTUL58eaFv377CtWvXFK8/ffpUeO+994SyZcsKbm5uQs+ePYX4+HiVfVjz5y+0bds2AYAQGxursry0ngN79uwRPfcHDx4sCEJBF/rJkycLAQEBgrOzs9CuXTu1Y/Po0SOhf//+goeHh+Dp6SkMHTpUSE9PV1nn7NmzQosWLQRnZ2ehfPnywuzZs0vqI+qk7RjcvHlT4/WhcHypkydPCpGRkYKXl5fg4uIi1KxZU/j8889VEgVBsNxjoO3zZ2ZmCh07dhT8/PwER0dHoVKlSsKIESPUHoBL8zlQ6KeffhJcXV2FlJQUte3NcQ7IBEEQDC9HIiIiIrJ+bCNERERENouJEBEREdksJkJERERks5gIERERkc1iIkREREQ2i4kQERER2SwmQkRERGSzmAgRUakUGhqKuXPnmjsMIrJwTISIyCI9fPgQTk5OePLkCXJzc+Hu7o7bt28rXg8NDYVMJoNMJoO7uzsaNGiAP/74Q/H68ePHVWa512bZsmXw9vaW+iMQkRVgIkREFunIkSOoW7cu3N3dcerUKfj4+KBixYoq68yYMQPx8fE4ffo0GjdujL59++Lw4cMAAD8/P7i5uZV43MoTQRKR5WMiREQW6fDhw2jevDkA4ODBg4qflZUpUwaBgYGoXr06FixYAFdXV/z7778A1KvGUlJS8PbbbyMgIAAuLi6oXbs2Nm7ciL1792Lo0KFITU1VlDBNmzYNACCTybB+/XqV9/T29sayZcsAAHFxcZDJZFizZg1at24NFxcXrFq1CgDw888/o2bNmnBxcUF4eDh++OEHaQ8QEUnCwdwBEBEVun37NurUqQMAyMzMhL29PZYtW4anT59CJpPB29sbAwYMEE0qHBwc4OjoiJycHLXX5HI5OnfujPT0dKxcuRJVqlTBpUuXYG9vj2bNmmHu3LmYMmUKYmNjAQAeHh4GxT1hwgTMmTMH9evXVyRDU6ZMwfz581G/fn2cPn0aI0aMgLu7OwYPHmzEkSEiU2EiREQWIzg4GGfOnEFaWhoaNWqEo0ePwt3dHfXq1cOmTZtQsWJF0SQlJycHc+bMQWpqKtq2bav2+s6dO3Hs2DFcvnwZ1atXBwBUrlxZ8bqXlxdkMhkCAwONinvs2LHo1auX4vepU6dizpw5imVhYWG4dOkSfvrpJyZCRBaGiRARWQwHBweEhoZi7dq1aNy4MerUqYNDhw4hICAArVq1Ult//PjxmDRpErKysuDh4YHZs2eja9euauudOXMGFSpUUCRBUmvUqJHi5ydPnuD69esYNmwYRowYoViel5cHLy8vk7w/ERmPiRARWYwXXngBt27dQm5uLuRyOTw8PJCXl4e8vDx4eHigUqVKuHjxomL9jz76CEOGDIGHhwcCAgIgk8lE9+vq6mpUPDKZDIIgqCwTawzt7u6u+DkjIwMAsHjxYkRGRqqsZ29vb1QcRGQ6TISIyGJs3rwZubm5aNeuHb788ks0bNgQ/fr1w5AhQxAVFQVHR0eV9X19fVG1alWd+61Tpw7u3r2LK1euiJYKOTk5IT8/X225n58f4uPjFb9fvXoVmZmZWt8rICAAwcHBuHHjBgYOHKgzNiIyLyZCRGQxKlWqhISEBDx48ADdu3eHTCbDxYsX0bt3bwQFBRm939atW6NVq1bo3bs3vvnmG1StWhUxMTGQyWSIiopCaGgoMjIysGvXLtStWxdubm5wc3ND27ZtMX/+fDRt2hT5+fkYP368WjImZvr06Rg9ejS8vLwQFRWF7OxsnDhxAo8fP0Z0dLTRn4OIpMfu80RkUfbu3YvGjRvDxcUFx44dQ4UKFYqVBBX666+/0LhxY/Tv3x+1atXC//73P0UpULNmzfDOO++gb9++8PPzw5dffgkAmDNnDkJCQtCyZUsMGDAA48aN02tsouHDh+Pnn3/G0qVLERERgdatW2PZsmUICwsr9ucgImnJhKIV4EREREQ2giVCREREZLOYCBEREZHNYiJERERENouJEBEREdksJkJERERks5gIERERkc1iIkREREQ2i4kQERER2SwmQkRERGSzmAgRERGRzWIiRERERDaLiRARERHZrP8DfHa8v1XWcjIAAAAASUVORK5CYII=",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[-0.0003  0.0402 -0.4679  0.423 ]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "plt.plot(res[:,2])\n",
     "plt.title('Deviation')\n",
@@ -2734,95 +1968,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:absl:Found untraced functions such as _jit_compiled_convolution_op, _jit_compiled_convolution_op, _jit_compiled_convolution_op while saving (showing 3 of 3). These functions will not be directly callable after loading.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "INFO:tensorflow:Assets written to: C:\\Users\\Muell\\AppData\\Local\\Temp\\tmpkd84dldu\\assets\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:tensorflow:Assets written to: C:\\Users\\Muell\\AppData\\Local\\Temp\\tmpkd84dldu\\assets\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "183756"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
+   "source": [
+    "model.export(\"test\", \"tf_saved_model\")  # replace tf.saved_model.save with this line"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "FileName = TFlite_MainType + \"_\" + TFlite_Version + \"_\" + TFlite_Size\n",
     "\n",
-    "converter = tf.lite.TFLiteConverter.from_keras_model(model)\n",
+    "converter = tf.lite.TFLiteConverter.from_saved_model(\"test\")\n",
     "tflite_model = converter.convert()\n",
     "open(FileName + \".tflite\", \"wb\").write(tflite_model)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:absl:Found untraced functions such as _jit_compiled_convolution_op, _jit_compiled_convolution_op, _jit_compiled_convolution_op while saving (showing 3 of 3). These functions will not be directly callable after loading.\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "INFO:tensorflow:Assets written to: C:\\Users\\Muell\\AppData\\Local\\Temp\\tmpy3h2x96q\\assets\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:tensorflow:Assets written to: C:\\Users\\Muell\\AppData\\Local\\Temp\\tmpy3h2x96q\\assets\n",
-      "C:\\Users\\Muell\\anaconda3\\envs\\py39-td-opencv\\lib\\site-packages\\tensorflow\\lite\\python\\convert.py:766: UserWarning: Statistics for quantized inputs were expected, but not specified; continuing anyway.\n",
-      "  warnings.warn(\"Statistics for quantized inputs were expected, but not \"\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ana-cont_1300_s2_q.tflite\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "53328"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from pathlib import Path\n",
     "import tensorflow as tf\n",
@@ -2834,7 +2004,7 @@
     "      data = np.expand_dims(x_data[5], axis=0)\n",
     "      yield [data.astype(np.float32)]\n",
     "        \n",
-    "converter2 = tf.lite.TFLiteConverter.from_keras_model(model)\n",
+    "converter = tf.lite.TFLiteConverter.from_saved_model(\"test\")\n",
     "converter2.optimizations = [tf.lite.Optimize.DEFAULT]\n",
     "converter2.representative_dataset = representative_dataset\n",
     "tflite_quant_model = converter2.convert()\n",
@@ -2868,7 +2038,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.11.8"
   },
   "vscode": {
    "interpreter": {
diff --git a/ana-cont_1300_s2.tflite b/ana-cont_1300_s2.tflite
index b8b72be8..35e705b8 100644
Binary files a/ana-cont_1300_s2.tflite and b/ana-cont_1300_s2.tflite differ
diff --git a/collectmeterdigits/__pycache__/__init__.cpython-311.pyc b/collectmeterdigits/__pycache__/__init__.cpython-311.pyc
new file mode 100644
index 00000000..1ff036e1
Binary files /dev/null and b/collectmeterdigits/__pycache__/__init__.cpython-311.pyc differ
diff --git a/collectmeterdigits/__pycache__/collect.cpython-311.pyc b/collectmeterdigits/__pycache__/collect.cpython-311.pyc
new file mode 100644
index 00000000..7fadf2f6
Binary files /dev/null and b/collectmeterdigits/__pycache__/collect.cpython-311.pyc differ
diff --git a/collectmeterdigits/__pycache__/glob.cpython-311.pyc b/collectmeterdigits/__pycache__/glob.cpython-311.pyc
new file mode 100644
index 00000000..427871ab
Binary files /dev/null and b/collectmeterdigits/__pycache__/glob.cpython-311.pyc differ
diff --git a/collectmeterdigits/__pycache__/labeling.cpython-311.pyc b/collectmeterdigits/__pycache__/labeling.cpython-311.pyc
new file mode 100644
index 00000000..24a20699
Binary files /dev/null and b/collectmeterdigits/__pycache__/labeling.cpython-311.pyc differ
diff --git a/collectmeterdigits/__pycache__/predict.cpython-311.pyc b/collectmeterdigits/__pycache__/predict.cpython-311.pyc
new file mode 100644
index 00000000..3a36dc06
Binary files /dev/null and b/collectmeterdigits/__pycache__/predict.cpython-311.pyc differ
diff --git a/data/HistoricHashData.txt b/data/HistoricHashData.txt
index eccde934..64d1232a 100644
--- a/data/HistoricHashData.txt
+++ b/data/HistoricHashData.txt
@@ -12945,3 +12945,1742 @@
 2024-03-30	abc	./data_raw_all/9.9_bba3e8309811f376c5c087bc57bc9763.jpg	efefe7e3e0c0d8c0
 2024-03-30	abc	./data_raw_all/9.9_cd0ec96bd0825a9fd05d157210d9a2ab.jpg	ffffffe08084c173
 2024-03-30	abc	./data_raw_all/9.9_fe08392177e40ab31a8be71885765c1a.jpg	ffff4f27c3420703
+2024-03-30	abc	./data_raw_all/0.0_0.0.jpg	ffe767e3c342bdd7
+2024-03-30	abc	./data_raw_all/0.0_0002_analog4_20200819-014811.jpg	3fa74703a367dfff
+2024-03-30	abc	./data_raw_all/0.0_0003_zeiger1_2019-06-04T044009.jpg	fff7c7e1c0c0c0b0
+2024-03-30	abc	./data_raw_all/0.0_0006_zeiger1_2020-04-29_10-56-43.jpg	f5f4e2e0e0e0d0c0
+2024-03-30	abc	./data_raw_all/0.0_0012_zeiger2_2019-06-06T113009.jpg	fcf6e7e1c140c0c0
+2024-03-30	abc	./data_raw_all/0.0_0013_zeiger2_2020-04-29_10-56-43.jpg	fff5e6a0e0e090c0
+2024-03-30	abc	./data_raw_all/0.0_0020_zeiger3_2019-06-05T201009.jpg	ffe7c781c1c080c0
+2024-03-30	abc	./data_raw_all/0.0_0022_zeiger3_2020-04-29_11-52-02.jpg	ffefe6c2c2429881
+2024-03-30	abc	./data_raw_all/0.0_0028_zeiger4_2019-06-04T134009.jpg	f9e7c78703031f7d
+2024-03-30	abc	./data_raw_all/0.0_0047_zeiger4_2019-06-05T024009.jpg	f9e7c78703431b7f
+2024-03-30	abc	./data_raw_all/0.0_0049_zeiger4_2020-04-29_14-03-02.jpg	fcf4e6e3e3e2dc15
+2024-03-30	abc	./data_raw_all/0.0_0079_zeiger4_2019-09-15_05-40-13.jpg	f9e70787c343ffff
+2024-03-30	abc	./data_raw_all/0.0_01bac1c349774fc888194436858a8b08.jpg	fde6e4c0e0f0e1e4
+2024-03-30	abc	./data_raw_all/0.0_04b173a2a89d74ae96e4619b8c91db33.jpg	a787070303071f17
+2024-03-30	abc	./data_raw_all/0.0_1436f278d267410af7a271427d08809e.jpg	ffff4727c3020303
+2024-03-30	abc	./data_raw_all/0.0_1cb245637a3e5d4455b895e0bee1c9c3.jpg	27270f0703070f0f
+2024-03-30	abc	./data_raw_all/0.0_28d6da835dad40feff650ce6d4481d3a.jpg	e3e7e2c0c2e2fcfd
+2024-03-30	abc	./data_raw_all/0.0_3c780c0d120747ec9cc07e204e47f6ac.jpg	ffe7e6c1c1e2dcd0
+2024-03-30	abc	./data_raw_all/0.0_427b900cf0702e5143d256c11f9bbc8e.jpg	f4f67663c8fe3c88
+2024-03-30	abc	./data_raw_all/0.0_557d5cc3b6660acee736809eec9df6e7.jpg	fee7674383a79f07
+2024-03-30	abc	./data_raw_all/0.0_6c945de891129c362c7542fe773ef1c6.jpg	a0e0e0c0e0f0f1f6
+2024-03-30	abc	./data_raw_all/0.0_759b6e62af23ccf905789eeb80c9f440.jpg	ffe7c1c0b8f0c000
+2024-03-30	abc	./data_raw_all/0.0_7b1744f5b607e692b5f383ec59f5f962.jpg	fffff7a18081c1f7
+2024-03-30	abc	./data_raw_all/0.0_8126c5939ecc0662f73ae6b912110973.jpg	a0c0e0c0e0f0f8fa
+2024-03-30	abc	./data_raw_all/0.0_ana2_20230501-181307.jpg	ffe7e7e3c0c0d8c0
+2024-03-30	abc	./data_raw_all/0.0_analog1_20200930-053003.jpg	f0f0f0e0e0f8e0c0
+2024-03-30	abc	./data_raw_all/0.0_analog3_20201011-043033.jpg	ffff6727271e0000
+2024-03-30	abc	./data_raw_all/0.0_b83c38e151a3a0496fee8ee2b09413c9.jpg	ffef47a7c3420503
+2024-03-30	abc	./data_raw_all/0.0_bf8d67ab08b7a77050011690d0ca0bbe.jpg	f7f2e3c1e3e2e77f
+2024-03-30	abc	./data_raw_all/0.0_e0941e6e3c5bf5a31d46bc38cb65648f.jpg	f7f76383e3e75f3f
+2024-03-30	abc	./data_raw_all/0.0_ec178d007e56e58e01df6088cdc8dc27.jpg	f7e7e3a3e3e77f3f
+2024-03-30	abc	./data_raw_all/0.0_pointer_20211009-181429.jpg	fff5f6f4e08080e0
+2024-03-30	abc	./data_raw_all/0.1_0.1.jpg	97276703c747ff7f
+2024-03-30	abc	./data_raw_all/0.1_0062_zeiger2_2020-06-15_04-59-11.jpg	fdf4f4e4e0f0c080
+2024-03-30	abc	./data_raw_all/0.1_0065_zeiger3_2019-11-19_10-17-03.jpg	efc7c787c5df8a00
+2024-03-30	abc	./data_raw_all/0.1_0077_zeiger3_2020-06-14_08-42-44.jpg	fff7e7e7e75e0000
+2024-03-30	abc	./data_raw_all/0.1_0122_zeiger3_2019-11-19_10-37-03.jpg	efe7c787c5dfc880
+2024-03-30	abc	./data_raw_all/0.1_040655bb94928dd447738cc3cb798c55.jpg	f7f7e383c3e66fd6
+2024-03-30	abc	./data_raw_all/0.1_0f14387787a991d941c19cdaea6d90fd.jpg	f5e2e2e1e060f4f4
+2024-03-30	abc	./data_raw_all/0.1_26f4b5de61a5a30a65752230065a261d.jpg	e7e74323234f8f27
+2024-03-30	abc	./data_raw_all/0.1_34446c9374edfd487bb7c7d113a22940.jpg	e7e7432323470f07
+2024-03-30	abc	./data_raw_all/0.1_3c3ccb4fffa362b4ff1b98c7c5f1d909.jpg	fde7e7c3c3425204
+2024-03-30	abc	./data_raw_all/0.1_4963_analog3_20200815-021824.jpg	fff7e3e3c3c2cbc5
+2024-03-30	abc	./data_raw_all/0.1_4991_zeiger4_2019-06-05T192009.jpg	fee7c70703031b7d
+2024-03-30	abc	./data_raw_all/0.1_5000_zeiger4_2019-06-06T153009.jpg	feefc78703431b7d
+2024-03-30	abc	./data_raw_all/0.1_508678d2fd3ac9c2f9505dc67a9c27ef.jpg	ffff67a7c7420703
+2024-03-30	abc	./data_raw_all/0.1_50a4ada862521034a777fdb8cbb27a9c.jpg	f7f7e74307071f0d
+2024-03-30	abc	./data_raw_all/0.1_540fb75deccbc60e1adcb47b3e0837f3.jpg	f7f7e383c3e74f3f
+2024-03-30	abc	./data_raw_all/0.1_707b7e24f27acb2a13c240fe4d1e5156.jpg	bfb7670303070504
+2024-03-30	abc	./data_raw_all/0.1_7ba85793833ccf1f0cdfb9d11aca17fe.jpg	ffffffc7c7808101
+2024-03-30	abc	./data_raw_all/0.1_ana4_20220628-040223.jpg	f7e763a3231f0f17
+2024-03-30	abc	./data_raw_all/0.1_f3d9ddc58b4f44272ff85c0500b791ff.jpg	ffff47a7c7420d03
+2024-03-30	abc	./data_raw_all/0.2_0027_zeiger4_2019-06-02T090009.jpg	fce7c78783431f7f
+2024-03-30	abc	./data_raw_all/0.2_0050_analog1_20200821-060242.jpg	dff5e382c3c6e9f7
+2024-03-30	abc	./data_raw_all/0.2_0081_analog1_20200820-233906.jpg	d7f7e382c3e6edf7
+2024-03-30	abc	./data_raw_all/0.2_0103_zeiger2_2019-11-19_02-07-03.jpg	efe7c787c5def8f0
+2024-03-30	abc	./data_raw_all/0.2_0132_analog4_20200813-223410.jpg	b7274303a3dfcff7
+2024-03-30	abc	./data_raw_all/0.2_0d37069a334b3c4ce4ac1c498497579c.jpg	1f170703071f1f3f
+2024-03-30	abc	./data_raw_all/0.2_243f03a371524f1c2217c47a10563f55.jpg	fef363a3e3e36f3f
+2024-03-30	abc	./data_raw_all/0.2_337e96f501366f1afd8da9b59a2aaf1c.jpg	eca76644c1e3bbe7
+2024-03-30	abc	./data_raw_all/0.2_3e6d4f91774a3437d482413d3430d52a.jpg	fcf6f6e6e63e3800
+2024-03-30	abc	./data_raw_all/0.2_56d937362f793a348cdf03d517b33ddb.jpg	f7f7e7c3c3465a04
+2024-03-30	abc	./data_raw_all/0.2_71cb15f34eae196cb16f3d7ca457c337.jpg	d1f1e2c0c2fff7ff
+2024-03-30	abc	./data_raw_all/0.2_7273ebd6222ca6f11a9efb89b164f666.jpg	f7e7e7e3c1c0b880
+2024-03-30	abc	./data_raw_all/0.2_8695ab6d3baaf381ca3e5099a6aae92f.jpg	f7f3e383c3e66f76
+2024-03-30	abc	./data_raw_all/0.2_97925fc48a53ffdc1771f9e310d9e9e3.jpg	ffffefe7c5808001
+2024-03-30	abc	./data_raw_all/0.2_ana2_20220629-153229.jpg	f7e7e383c3c3c5f4
+2024-03-30	abc	./data_raw_all/0.2_b996a82eca0579959c32b800815d045b.jpg	fffff7838084c173
+2024-03-30	abc	./data_raw_all/0.2_bd3b98108d206cad289689c9047c48f7.jpg	f5f2e2e1c1e2f4f4
+2024-03-30	abc	./data_raw_all/0.2_c0a3ae930cb0b17ed7ccd047ce19c031.jpg	f7f7e763070f0f07
+2024-03-30	abc	./data_raw_all/0.2_c3af6af151a91351162ed03ca7fc984f.jpg	f7e5e3c3c3e7777d
+2024-03-30	abc	./data_raw_all/0.2_pointer_20211010-214243.jpg	fff5f6f6c08080c0
+2024-03-30	abc	./data_raw_all/0.3_0.2.jpg	fff7e7e2c2809181
+2024-03-30	abc	./data_raw_all/0.3_0084_analog2_20200816-221937.jpg	fff7e382c382c9d7
+2024-03-30	abc	./data_raw_all/0.3_0085_analog4_20200815-190815.jpg	3fa7c7038367dfef
+2024-03-30	abc	./data_raw_all/0.3_0099_zeiger1_2020-06-14_14-12-08.jpg	f0f0f0e4e4d8c081
+2024-03-30	abc	./data_raw_all/0.3_0101_zeiger2_2019-09-14_19-40-12.jpg	7cf7e7a3e343fff7
+2024-03-30	abc	./data_raw_all/0.3_0104_zeiger2_2019-11-19_10-57-03.jpg	f7e7c787c5fef8f0
+2024-03-30	abc	./data_raw_all/0.3_0126_zeiger3_2020-06-14_08-28-47.jpg	fff777e767580000
+2024-03-30	abc	./data_raw_all/0.3_012c4abd3227a28a4c7044549534cb19.jpg	f7f3e3a3e3e36f3f
+2024-03-30	abc	./data_raw_all/0.3_0148_zeiger3_2019-06-04T073009.jpg	fff7c3a1c1c080c0
+2024-03-30	abc	./data_raw_all/0.3_0176_zeiger4_2019-11-19_11-02-03.jpg	f7e743a3e3fbffff
+2024-03-30	abc	./data_raw_all/0.3_08561e46e692093b4b273c89f3679fd3.jpg	f3f3e2c0c0e2fcf5
+2024-03-30	abc	./data_raw_all/0.3_0e81959dc0e81e5f79710399becf8440.jpg	f0f67263c9fc3c80
+2024-03-30	abc	./data_raw_all/0.3_2ba2a542233f9d7688ae673c5b1b3e30.jpg	fff7e6c3c3465001
+2024-03-30	abc	./data_raw_all/0.3_44325e462ba5ecbe224f05b023527f83.jpg	f0f67263c8fc3c98
+2024-03-30	abc	./data_raw_all/0.3_9b30e11a37eae61bbbf6ccf9f7e75f6f.jpg	b4670320f0ffffff
+2024-03-30	abc	./data_raw_all/0.3_a4afe607772dd575cc1e7c36422dc541.jpg	fff7e6c3c2e2fcf0
+2024-03-30	abc	./data_raw_all/0.3_a7df1a5ee8d60c0c81e4cfd8e2e10efa.jpg	f0f0e0e0e0f0c0fc
+2024-03-30	abc	./data_raw_all/0.3_ac562e437f56d107dfcd96311fff6d9b.jpg	f1f2e2e1e0e2f4f5
+2024-03-30	abc	./data_raw_all/0.3_cd71bbf0a0013858549d7a46fe96dd67.jpg	fff3e3a3c3e37f3f
+2024-03-30	abc	./data_raw_all/0.3_f38f2eb5263c3f8159ae2d2a7168d5d5.jpg	fff3e7e3e3fff43e
+2024-03-30	abc	./data_raw_all/0.4_0.3.jpg	fff3e3e3c2809183
+2024-03-30	abc	./data_raw_all/0.4_0.4.jpg	fff767c7c742bfbb
+2024-03-30	abc	./data_raw_all/0.4_0127_zeiger4_2019-06-02T100009.jpg	f9f7c78783431f7f
+2024-03-30	abc	./data_raw_all/0.4_0161_zeiger2_2020-04-29_12-08-02.jpg	fff7e2a0e0e290c0
+2024-03-30	abc	./data_raw_all/0.4_0163_zeiger3_2019-09-14_23-10-12.jpg	fff7c6a3c342d7ff
+2024-03-30	abc	./data_raw_all/0.4_0175_zeiger4_2019-11-19_07-22-03.jpg	f3e343a3e3fbdfff
+2024-03-30	abc	./data_raw_all/0.4_0179_analog4_20200815-171449.jpg	bfb343238367dfff
+2024-03-30	abc	./data_raw_all/0.4_0205_zeiger4_2019-11-19_06-52-03.jpg	f3e343a3e7ffbfff
+2024-03-30	abc	./data_raw_all/0.4_14fec4da417bf876a7c78fef56b422b9.jpg	fff3e2e1e0e2fcd0
+2024-03-30	abc	./data_raw_all/0.4_3833782a254a343355a914b075af7e7b.jpg	fff7672707020d07
+2024-03-30	abc	./data_raw_all/0.4_5a12776d8fe12d10281ee866ccf9548e.jpg	f7f3e1a1c3e66ff6
+2024-03-30	abc	./data_raw_all/0.4_8bf927e69af366b1ac02d6e0a233a629.jpg	fff7772707020707
+2024-03-30	abc	./data_raw_all/0.4_a0124fab8ccc2580f36474055e95210c.jpg	fff7772787020701
+2024-03-30	abc	./data_raw_all/0.4_a6e16cc4dc00ffaef17172aa43d72124.jpg	f7f2e4c0e0e0e1e4
+2024-03-30	abc	./data_raw_all/0.4_ad16a3e8bd781b60d6b7e44982175b89.jpg	e0c0e0c0e0f0f9f2
+2024-03-30	abc	./data_raw_all/0.4_ana1_20220625-132710.jpg	b7f3c383c544cbf7
+2024-03-30	abc	./data_raw_all/0.4_dabf5982cdfd1f93f76861ef28c47e81.jpg	b6360720f0fcffff
+2024-03-30	abc	./data_raw_all/0.4_e9ca2dc145e6c8fe78ad9dd80d2b218a.jpg	d1d1e0c0c2f7f7ff
+2024-03-30	abc	./data_raw_all/0.4_f39d723e2132a87b91534429b2aa6687.jpg	f7e3432303570f27
+2024-03-30	abc	./data_raw_all/0.4_pointer_20211010-021111.jpg	fffbf6f6008080e0
+2024-03-30	abc	./data_raw_all/0.5_0.6.jpg	9e376703c747ff7f
+2024-03-30	abc	./data_raw_all/0.5_0156_zeiger1_2019-06-04T094009.jpg	fff3c3c1c0c0c0b0
+2024-03-30	abc	./data_raw_all/0.5_0169_zeiger4_2019-06-03T032009.jpg	fef7c78303031b7d
+2024-03-30	abc	./data_raw_all/0.5_0191_zeiger2_2019-06-04T161009.jpg	fdf2e3e1c140c0c0
+2024-03-30	abc	./data_raw_all/0.5_0198_zeiger2_2020-06-14_11-32-34.jpg	fdf0f2e0e0f0c080
+2024-03-30	abc	./data_raw_all/0.5_0204_zeiger4_2019-09-15_05-49-06.jpg	fef7e787c343ffff
+2024-03-30	abc	./data_raw_all/0.5_0212_zeiger4_2020-04-29_13-05-02.jpg	f8f6e2e3e3e2dc15
+2024-03-30	abc	./data_raw_all/0.5_286e3de251c54b44785520209af7bb49.jpg	f0f2e0e0e0e0e0e4
+2024-03-30	abc	./data_raw_all/0.5_2bcf254ad1249c8e657903f4cc8a4760.jpg	fff7772787060f03
+2024-03-30	abc	./data_raw_all/0.5_662f152c1717b7a81b1b11ff5b4d919c.jpg	f7f3e181c3e6e7d6
+2024-03-30	abc	./data_raw_all/0.5_6689e925ce5da001263a63a7120f885d.jpg	ffff772303070f05
+2024-03-30	abc	./data_raw_all/0.5_8ab7aa308a7c5ed835e82c4d2b3723b0.jpg	fff7e2e0c0e0f0e0
+2024-03-30	abc	./data_raw_all/0.5_a034da8ed62432da9ecfd754300454e5.jpg	fbf3632303570f27
+2024-03-30	abc	./data_raw_all/0.5_analog2_20200930-052612.jpg	fffcf0e4e0c08080
+2024-03-30	abc	./data_raw_all/0.5_e77bfff70aae7ec0e5a15b062b3e7ea4.jpg	f8f27263d9fc3c80
+2024-03-30	abc	./data_raw_all/0.5_f16339267a2218779d64c54e6868d615.jpg	f7f3632303438f27
+2024-03-30	abc	./data_raw_all/0.6_0234_zeiger4_2019-06-05T163009.jpg	fbf7c38303031b7d
+2024-03-30	abc	./data_raw_all/0.6_0bd21d49f293688103ee79226ffe50a7.jpg	feb362c4c1e3bbe7
+2024-03-30	abc	./data_raw_all/0.6_0c26f0dcb7dcf8d106a5b66b53267ee8.jpg	fbf7e7e3c180b881
+2024-03-30	abc	./data_raw_all/0.6_32225ac95bac1f907f5a565e9846a7c7.jpg	fef973a3c3f36f3f
+2024-03-30	abc	./data_raw_all/0.6_328363d6e68558ceae7024167ba70acf.jpg	2f27030703070f8f
+2024-03-30	abc	./data_raw_all/0.6_32ef685c975b1322a248c01dc76d55b4.jpg	fff373a3c3f36f3f
+2024-03-30	abc	./data_raw_all/0.6_3816262cfbfc52f5da85b8f21e0e4efd.jpg	2f07030703070f07
+2024-03-30	abc	./data_raw_all/0.6_4e2893dbd109753be2b792ef22e31ad1.jpg	fffff6838089c1f7
+2024-03-30	abc	./data_raw_all/0.6_5367ed7438cbf4365041548e310a2416.jpg	f9f0f2e1613e1f1f
+2024-03-30	abc	./data_raw_all/0.6_6a517ddd6260406cd48d9dccf644d6d1.jpg	fbf2e4c0e0e8e1e4
+2024-03-30	abc	./data_raw_all/0.6_6e1b1ef0964ebfb97141d4b346d080f7.jpg	f9f2e2e1c160fcf4
+2024-03-30	abc	./data_raw_all/0.6_7516b7fc7381416cc42913c399670d90.jpg	fff3e3a3c3f76f3f
+2024-03-30	abc	./data_raw_all/0.6_91ed4390257db3722ef6c98256d7052d.jpg	fff776a7c7020f03
+2024-03-30	abc	./data_raw_all/0.6_b56de36bc44f7b3e773a60a8226cafb5.jpg	fc120721f0f8ffff
+2024-03-30	abc	./data_raw_all/0.7.jpg	fffbf3e382a08183
+2024-03-30	abc	./data_raw_all/0.7_0214_analog4_20200814-161117.jpg	bf7343a3e3f7cff7
+2024-03-30	abc	./data_raw_all/0.7_0233_zeiger4_2019-06-05T054009.jpg	fef7c383c3431f7f
+2024-03-30	abc	./data_raw_all/0.7_0255_zeiger3_2020-06-14_17-18-15.jpg	fffff7e7675a0000
+2024-03-30	abc	./data_raw_all/0.7_0256_zeiger4_2019-09-15_05-00-12.jpg	f9f30383c343ffff
+2024-03-30	abc	./data_raw_all/0.7_0257_zeiger4_2020-04-29_10-58-40.jpg	fef2e2e3e3e2dc15
+2024-03-30	abc	./data_raw_all/0.7_0258_analog3_20200817-155337.jpg	fffff3e3c3c6cbc5
+2024-03-30	abc	./data_raw_all/0.7_0287_zeiger3_2020-04-29_10-56-43.jpg	fff7e2c2c2429881
+2024-03-30	abc	./data_raw_all/0.7_0c18d8543212849fc781a8111beedcf0.jpg	fffff7e7c7000001
+2024-03-30	abc	./data_raw_all/0.7_11e94ec62eb5a1eaf8db39a2304d177d.jpg	ffe7c1a0f0f0c000
+2024-03-30	abc	./data_raw_all/0.7_14044204a806f14027a115a594dfd3a7.jpg	f7f1e1c3c2e7e7fd
+2024-03-30	abc	./data_raw_all/0.7_15ee9bd9c9e0d8135d50a3b7d2859135.jpg	fbf3e3e383a0b981
+2024-03-30	abc	./data_raw_all/0.7_1e8c4a9bd7146c1556f3dfc4429c8e88.jpg	3c130723f0f8feff
+2024-03-30	abc	./data_raw_all/0.7_25fd88d819c64c3e30558f07e3ea69b8.jpg	f9f3e2e0c0e2f4fd
+2024-03-30	abc	./data_raw_all/0.7_2e6228a6bd844b71e32a31f566e3698a.jpg	fdf3f2a1c3e2d4b4
+2024-03-30	abc	./data_raw_all/0.7_3abe52800519d7849e381244c5e543d8.jpg	f3f2e0c0e0f8e1e4
+2024-03-30	abc	./data_raw_all/0.7_41690d0a76a3ffafcebb04e72fc3ba06.jpg	f8fa72437bf83c90
+2024-03-30	abc	./data_raw_all/0.7_91bf08d70a5db97ffa24f23ebecabded.jpg	fff3e2e3c3425000
+2024-03-30	abc	./data_raw_all/0.7_abd8b66423f52745052a30c53de88fe7.jpg	f9f8f2e1612f1f1f
+2024-03-30	abc	./data_raw_all/0.7_ana4_20220624-155205.jpg	fbf363a3673f0f07
+2024-03-30	abc	./data_raw_all/0.7_bb903b14ec439cdff7ba2573b64ac4e0.jpg	fffff7e7c4800101
+2024-03-30	abc	./data_raw_all/0.7_f3e85806fb876445ba5f246fc8ada910.jpg	f7f3e3c3c7e7f7fd
+2024-03-30	abc	./data_raw_all/0.7_pointer_20211008-185559.jpg	fffbf2f6808080c0
+2024-03-30	abc	./data_raw_all/0.8_0012467e8c0878b9ead3759bd298bc88.jpg	9793030303079f17
+2024-03-30	abc	./data_raw_all/0.8_020cf5e2f6f66a8360749047aba87a35.jpg	b793030303071f97
+2024-03-30	abc	./data_raw_all/0.8_0282_zeiger2_2020-04-29_13-27-02.jpg	fffdf2a0e0e090c0
+2024-03-30	abc	./data_raw_all/0.8_0286_zeiger3_2019-11-19_11-02-03.jpg	fff3c387e5ffc880
+2024-03-30	abc	./data_raw_all/0.8_0289_zeiger3_2020-06-14_09-27-48.jpg	fffb73e7e75a0000
+2024-03-30	abc	./data_raw_all/0.8_0294_zeiger4_2019-06-06T162009.jpg	feffc38303431b7d
+2024-03-30	abc	./data_raw_all/0.8_0300_zeiger4_2019-09-15_05-10-12.jpg	fcf7e383c3c3ffff
+2024-03-30	abc	./data_raw_all/0.8_0381_zeiger4_2020-04-29_13-32-02.jpg	fcffe2e3e3e2dc15
+2024-03-30	abc	./data_raw_all/0.8_16d48ad349dd9c7428a0fd445afb53de.jpg	ffbf7627c7020301
+2024-03-30	abc	./data_raw_all/0.8_231f631b6c58bf2e92e0a487cbd30737.jpg	ffffdf838188c177
+2024-03-30	abc	./data_raw_all/0.8_483c116e580e577fe073f4cc9ce261e3.jpg	ffff76a7c7420503
+2024-03-30	abc	./data_raw_all/0.8_73bf1a353abcf5349073106bc7064211.jpg	fefb636383a79f17
+2024-03-30	abc	./data_raw_all/0.8_ana4_20220625-105710.jpg	fff363a3271f0f07
+2024-03-30	abc	./data_raw_all/0.8_ana4_20220629-153729.jpg	fff971a1633f0f97
+2024-03-30	abc	./data_raw_all/0.8_f0eace7721f12d64fff0d256b2251b44.jpg	ffffde838189c1f7
+2024-03-30	abc	./data_raw_all/0.8_pointer_20211015-115250.jpg	fff9fab6028080e0
+2024-03-30	abc	./data_raw_all/0.9_0.8.jpg	fffbf3c383a20183
+2024-03-30	abc	./data_raw_all/0.9_0268_zeiger1_2019-06-04T150009.jpg	fff5c7a3c0c0c0b0
+2024-03-30	abc	./data_raw_all/0.9_0290_zeiger4_2019-06-02T093009.jpg	fcfec38383431f7f
+2024-03-30	abc	./data_raw_all/0.9_0301_analog2_20200822-140935.jpg	fff9e180c326c1d5
+2024-03-30	abc	./data_raw_all/0.9_0303_zeiger1_2019-06-04T154009.jpg	ffffc381c0c0c0b0
+2024-03-30	abc	./data_raw_all/0.9_0315_zeiger1_2020-06-14_14-16-42.jpg	f0f8f0e0e4f8c081
+2024-03-30	abc	./data_raw_all/0.9_0383_analog3_20200818-130925.jpg	fffff1e1c3c6cbd5
+2024-03-30	abc	./data_raw_all/0.9_0397_zeiger2_2019-11-19_11-07-03.jpg	ffe3c387cdfef8f0
+2024-03-30	abc	./data_raw_all/0.9_0d6778de9cf2c5fe59353ae0ed3d80fe.jpg	3e1203a3f1f1fdff
+2024-03-30	abc	./data_raw_all/0.9_1e1127c21f0b0afea0610ab0b48f9bec.jpg	fdf1e0e1e060f4f4
+2024-03-30	abc	./data_raw_all/0.9_2a129ac8cc0d5d8e4cfed72d3f920fe7.jpg	fff9e383c3f74f3f
+2024-03-30	abc	./data_raw_all/0.9_2d1a4f1673274f3e909e7fc666ce3d55.jpg	bffb630303070504
+2024-03-30	abc	./data_raw_all/0.9_674b6e5f8055a132d91120dc142be6f7.jpg	f8fa7203fbfa3880
+2024-03-30	abc	./data_raw_all/0.9_953f5bb5d4f71790c56c6fbcd2530305.jpg	fbf3e3c383313981
+2024-03-30	abc	./data_raw_all/0.9_ad6eb46fa43f56ab6a8a4f16137a8abd.jpg	3c1303a3f1f0fcff
+2024-03-30	abc	./data_raw_all/0.9_analog2_20201005-212133.jpg	fef8f0e0e0c08080
+2024-03-30	abc	./data_raw_all/0.9_analog3_20201013-060228.jpg	ffff7327271a0000
+2024-03-30	abc	./data_raw_all/0.9_d7792ee7261d388d9f45ac627b7bc041.jpg	bfbb670303070704
+2024-03-30	abc	./data_raw_all/0.9_df601c5ad68872a87055430235872f1b.jpg	fdf3e3c3c3475204
+2024-03-30	abc	./data_raw_all/0.9_ee11f5d52cb26d4efeaab150ed06a80c.jpg	2f2b030703070f0f
+2024-03-30	abc	./data_raw_all/1.0.jpg	fffff3c283220383
+2024-03-30	abc	./data_raw_all/1.0_0377_zeiger4_2019-06-06T151009.jpg	f9ffc38303431b7d
+2024-03-30	abc	./data_raw_all/1.0_0382_analog2_20200819-122209.jpg	fffde180c3a6c1d7
+2024-03-30	abc	./data_raw_all/1.0_0384_zeiger1_2019-06-04T171009.jpg	fffdc3c1c0c0c030
+2024-03-30	abc	./data_raw_all/1.0_0396_zeiger2_2019-09-15_06-10-12.jpg	7dfbd3a3c342d7ff
+2024-03-30	abc	./data_raw_all/1.0_0399_zeiger2_2020-06-14_08-47-20.jpg	fdfcf0e0e0f0c080
+2024-03-30	abc	./data_raw_all/1.0_0419_zeiger4_2019-11-19_09-47-03.jpg	fff16383e5ffdfff
+2024-03-30	abc	./data_raw_all/1.0_09957b3bdd2bb0b3e3a9971f9d9ebb7a.jpg	fffbe2c3c3464800
+2024-03-30	abc	./data_raw_all/1.0_0beb132454ae5c67cc9560ac64e404fc.jpg	f7f8e1c1c3e2e7fe
+2024-03-30	abc	./data_raw_all/1.0_105f0d6bdeabe277071ebe2ae97364e8.jpg	fff9f2c1c2e2dcd0
+2024-03-30	abc	./data_raw_all/1.0_14abf2218e4b8b4cc9e88b102181f0f9.jpg	ffff7227c7020503
+2024-03-30	abc	./data_raw_all/1.0_1ba964d23e8caf55f0cf81112da1123a.jpg	fcf8720373fa3880
+2024-03-30	abc	./data_raw_all/1.0_2d65e567e0b0824ea75c89fc318f6d96.jpg	fdf9e0e1c1e0f6f4
+2024-03-30	abc	./data_raw_all/1.0_37ca8424db2384f65fbea4c278c8e0b5.jpg	f7f9e181c3e6eff6
+2024-03-30	abc	./data_raw_all/1.0_6f030c68347e053c1762bdd8caedd26a.jpg	fcf8f2e6e63e3820
+2024-03-30	abc	./data_raw_all/1.0_8972788606b6c2b38958429d86874f0a.jpg	fdf9f3e1c3e2d0b4
+2024-03-30	abc	./data_raw_all/1.0_8d94cfcae73b21a264e0f9b63b768cb9.jpg	ecbb6240c1e3bbef
+2024-03-30	abc	./data_raw_all/1.0_a755ce1872fc7b45fc681b8f4760d3c7.jpg	f9f9e0e1e0e2f4f5
+2024-03-30	abc	./data_raw_all/1.0_ana3_20220623-140701.jpg	fff3c383c566cb1c
+2024-03-30	abc	./data_raw_all/1.0_b7789a104ba1512426abcb4d7a13565d.jpg	2f2f130703070f87
+2024-03-30	abc	./data_raw_all/1.0_db37d92ad06667b349228fc2b6a27060.jpg	f7f1e1c3c2e7777d
+2024-03-30	abc	./data_raw_all/1.0_e8da5d55b889daa7071b93296b6f15b6.jpg	fffbf2c3c2e2fcb0
+2024-03-30	abc	./data_raw_all/1.0_pointer_20211007-211907.jpg	fffdf882028080e0
+2024-03-30	abc	./data_raw_all/1.0_pointer_20211008-235058.jpg	fff9fa92068080c0
+2024-03-30	abc	./data_raw_all/1.1_018404edfcb68bb1405fd68358650797.jpg	fffbf2c0e0e0f0e0
+2024-03-30	abc	./data_raw_all/1.1_03a9706c07cb4ae369f754fa6244f9d9.jpg	fffbf38383733981
+2024-03-30	abc	./data_raw_all/1.1_0425_analog4_20200816-200113.jpg	bff94101c377cfe7
+2024-03-30	abc	./data_raw_all/1.1_0438_zeiger1_2020-04-29_12-24-02.jpg	f5f8e0e0e0e0d0c0
+2024-03-30	abc	./data_raw_all/1.1_0440_zeiger2_2019-06-04T024009.jpg	fdfee1e1c140c0c0
+2024-03-30	abc	./data_raw_all/1.1_0458_zeiger2_2019-11-19_11-42-03.jpg	fff3c387cddef8e0
+2024-03-30	abc	./data_raw_all/1.1_0501_zeiger3_2020-06-14_14-22-28.jpg	fffffbe7e75a0000
+2024-03-30	abc	./data_raw_all/1.1_0529_zeiger4_2020-04-29_12-14-02.jpg	fcfcf2e3e3e2dc15
+2024-03-30	abc	./data_raw_all/1.1_1db5d135ec483f111501d7594f15cecd.jpg	fffd71a1c3f36f3f
+2024-03-30	abc	./data_raw_all/1.1_2604bae91a10d999f094a7ee87205f56.jpg	ffbf7b2387020301
+2024-03-30	abc	./data_raw_all/1.1_5e93cac2f1ac3dd0db24a3b26a56a3f3.jpg	a0f0e0c0e0f0f9fa
+2024-03-30	abc	./data_raw_all/1.1_616c8d0c4b00b9b2d2b2dec7805f1b21.jpg	3e1a03e3f3f1f9fd
+2024-03-30	abc	./data_raw_all/1.1_6bbda73421b91da8a0d2cfebbe4f7eb5.jpg	f7fce1c1c1f2e77e
+2024-03-30	abc	./data_raw_all/1.1_analog1_20200928-055904.jpg	f0f8f8f0e0f8e0c0
+2024-03-30	abc	./data_raw_all/1.1_e7c027b1c799bb75afb34e6ca25befb2.jpg	fdf8f0e1c2e0f6f4
+2024-03-30	abc	./data_raw_all/1.1_e7f7d50ef31f40cf0287bf392636fff4.jpg	ffff9fb727388000
+2024-03-30	abc	./data_raw_all/1.2.jpg	0f3f6303c747bf7f
+2024-03-30	abc	./data_raw_all/1.2_0349c2d8f3f1853a9335d9fbf0d140c5.jpg	fff8e0c0e0f8e1e4
+2024-03-30	abc	./data_raw_all/1.2_0504_analog3_20200814-134221.jpg	fffde181c326cbf7
+2024-03-30	abc	./data_raw_all/1.2_0522_zeiger2_2020-06-15_13-04-07.jpg	fcfcf8e0e4f0c080
+2024-03-30	abc	./data_raw_all/1.2_0525_zeiger3_2019-06-02T182009.jpg	ffffc181c1c080c0
+2024-03-30	abc	./data_raw_all/1.2_1.1.jpg	fffff1c183220383
+2024-03-30	abc	./data_raw_all/1.2_1135fe85e936d64f12c69af151c21014.jpg	fff9610327078f27
+2024-03-30	abc	./data_raw_all/1.2_2ee414c49346f1b14fd69c40040db427.jpg	2f2f130307070f0f
+2024-03-30	abc	./data_raw_all/1.2_3550038cd33d743750e64ab6a716be90.jpg	f7fde1c3c3e7577d
+2024-03-30	abc	./data_raw_all/1.2_3f446ec07096e5767bf1d75ea299ae24.jpg	fdf9e1c3c3665204
+2024-03-30	abc	./data_raw_all/1.2_46ba7365d61db514d4e7c8f88a4532d0.jpg	f7fde181c3e667f6
+2024-03-30	abc	./data_raw_all/1.2_4f71f45fdc322b6f6bc4503f150fccd5.jpg	fffde2c3c3465200
+2024-03-30	abc	./data_raw_all/1.2_5cd10bb48633ffaa5d8e9d333126c5ee.jpg	fcfc0063f7fa3880
+2024-03-30	abc	./data_raw_all/1.2_7c781f90511181f7aa3fdbeb95b2c188.jpg	f7fee0c1e1f2e77e
+2024-03-30	abc	./data_raw_all/1.2_bd7c16dba8d09d1871fa7f26c542d7cb.jpg	ffffe0c0e0f0f0e0
+2024-03-30	abc	./data_raw_all/1.2_fc13b33bb4b8e920cb9b005e970e1b96.jpg	e0d0e0c0e0f0f1fe
+2024-03-30	abc	./data_raw_all/1.2_main_ana3_20221213-120635.jpg	ffff9f07070301e1
+2024-03-30	abc	./data_raw_all/1.2_main_ana3_20221214-180621.jpg	ffff9f03070381c1
+2024-03-30	abc	./data_raw_all/1.3_0129d319492d9e912f7d10f9541a8466.jpg	fcfcf8e2e63e3800
+2024-03-30	abc	./data_raw_all/1.3_0527_zeiger4_2019-11-19_06-17-03.jpg	fff94183e5ff9fff
+2024-03-30	abc	./data_raw_all/1.3_0556_zeiger3_2019-06-01T161012.jpg	ffffc1a1c1c0d1c0
+2024-03-30	abc	./data_raw_all/1.3_0560_zeiger4_2019-06-06T172010.jpg	f9ffc38383431f7f
+2024-03-30	abc	./data_raw_all/1.3_0635_zeiger4_2020-04-29_11-42-02.jpg	fefee0e3e3e2dc15
+2024-03-30	abc	./data_raw_all/1.3_0b85618e40775c67e0e36199b60219db.jpg	fedfde838389c1ff
+2024-03-30	abc	./data_raw_all/1.3_0c71e18c9553ab75038ad886967e82f1.jpg	fff9e0c0c2e2fcfd
+2024-03-30	abc	./data_raw_all/1.3_1fe175f541247c9266791695b0689d43.jpg	ffe7c3f0f0e0c000
+2024-03-30	abc	./data_raw_all/1.3_24a40f05cd9fffe0b337dc2daf181134.jpg	f7fde0c1c3e667d6
+2024-03-30	abc	./data_raw_all/1.3_3d63d0a84ad77822527e8afc985fed7d.jpg	ffdf9e838389c1f7
+2024-03-30	abc	./data_raw_all/1.3_57583a09c5a5bb39ab92b6cf552e2295.jpg	f4d0e0c0e0f0f0f0
+2024-03-30	abc	./data_raw_all/1.3_57a3f9688d965abb07982f7114e83334.jpg	1e0e83e3f3f1f1f9
+2024-03-30	abc	./data_raw_all/1.3_6ab79171f15ffb8a00229297c5294aaa.jpg	979d010303071f17
+2024-03-30	abc	./data_raw_all/1.3_72a43afaa2ba0adf483c81cfca86aceb.jpg	fff9f38323733993
+2024-03-30	abc	./data_raw_all/1.3_8f5d645eb52c3330715740a1988ac313.jpg	ffdfcf838389c177
+2024-03-30	abc	./data_raw_all/1.3_ana2_20220629-153729.jpg	fffde181e3c7c5f4
+2024-03-30	abc	./data_raw_all/1.3_b2ec01bb4eba162990f76e7973226416.jpg	ffff78a387020d03
+2024-03-30	abc	./data_raw_all/1.3_e8f50deb1ed585e7bf549144c9735986.jpg	fffdf181c3f74f3f
+2024-03-30	abc	./data_raw_all/1.3_pointer_20211016-125747.jpg	fffdb982068080e0
+2024-03-30	abc	./data_raw_all/1.4.jpg	fffff98103220383
+2024-03-30	abc	./data_raw_all/1.4_0555_zeiger2_2019-11-19_17-27-04.jpg	fffbc383cddef8f0
+2024-03-30	abc	./data_raw_all/1.4_0567_analog4_20200816-225334.jpg	3fbf51018367cfff
+2024-03-30	abc	./data_raw_all/1.4_0590_zeiger4_2019-06-02T171009.jpg	feffc18383031b7f
+2024-03-30	abc	./data_raw_all/1.4_0634_zeiger4_2020-04-29_11-26-02.jpg	fcfdf1e3e3e2dc15
+2024-03-30	abc	./data_raw_all/1.4_0dddd893997cfe7801e84fa2b5708be3.jpg	bfbf610303070704
+2024-03-30	abc	./data_raw_all/1.4_22d5eb55967748abe10a55821c2b7ba6.jpg	fffdf0e1c2e2fcf0
+2024-03-30	abc	./data_raw_all/1.4_2523f79e884b002190ccfb44a321beac.jpg	fcfc0063f7fe3280
+2024-03-30	abc	./data_raw_all/1.4_26fbdf938538453083cafc4a4f4f502b.jpg	fffcf0e1c0e0dcd0
+2024-03-30	abc	./data_raw_all/1.4_3716f1cf8c7fafec08541cf375679bef.jpg	ffff782307020503
+2024-03-30	abc	./data_raw_all/1.4_3c31166484058434214e72d05572c6b7.jpg	fffcf0e1c3e2d4b4
+2024-03-30	abc	./data_raw_all/1.4_4204f625a82f0b0a3cb1a45368a55f53.jpg	ffffffe3c5000101
+2024-03-30	abc	./data_raw_all/1.4_44a885c219661c684c011c942bdee88a.jpg	fdfce0e1c2e0fef4
+2024-03-30	abc	./data_raw_all/1.4_80e43730e07e5b9502c4b2881bad93d5.jpg	fff9d18363733b93
+2024-03-30	abc	./data_raw_all/1.4_analog2_20200926-075840.jpg	fffcf8e0e4d08080
+2024-03-30	abc	./data_raw_all/1.4_pointer_20211011-145832.jpg	ffbd9882068080e0
+2024-03-30	abc	./data_raw_all/1.5_0589_zeiger4_2019-06-01T151226.jpg	fcffc38343431f1f
+2024-03-30	abc	./data_raw_all/1.5_0639_analog1_20200814-151314.jpg	d7fde1c1c2e5fdf7
+2024-03-30	abc	./data_raw_all/1.5_0640_analog1_20200817-043822.jpg	dfffe180c3e6e5ff
+2024-03-30	abc	./data_raw_all/1.5_0672_zeiger3_2019-11-19_19-52-04.jpg	fffbc183e5dfc800
+2024-03-30	abc	./data_raw_all/1.5_0673_zeiger4_2020-04-29_12-18-02.jpg	fcfff0e1e3e2dc15
+2024-03-30	abc	./data_raw_all/1.5_0674_zeiger4_2020-04-29_13-27-02.jpg	f8fee0e1e3e2dc15
+2024-03-30	abc	./data_raw_all/1.5_0691_zeiger2_2020-04-29_11-29-02.jpg	fffde0a0c0e090c0
+2024-03-30	abc	./data_raw_all/1.5_0698_zeiger3_2019-11-19_19-02-04.jpg	fffbc183e5dfea80
+2024-03-30	abc	./data_raw_all/1.5_0759_zeiger3_2020-04-29_11-37-01.jpg	ffffe0c1c2429881
+2024-03-30	abc	./data_raw_all/1.5_0b27e29bebde84098201cf20d3de76f3.jpg	ffff7c2347020303
+2024-03-30	abc	./data_raw_all/1.5_0ce3dca825124f04f02a648b41322651.jpg	ffff9fb367780000
+2024-03-30	abc	./data_raw_all/1.5_11b0cacada8c701d2269706b1191fe19.jpg	1e8e81e3f3f3f3f9
+2024-03-30	abc	./data_raw_all/1.5_19ba84bf1ef14e425357d5b04f8637b7.jpg	ffffe1c1c3425204
+2024-03-30	abc	./data_raw_all/1.5_24ac24c8fa8d725cba874627dd12b058.jpg	fffdc18363733393
+2024-03-30	abc	./data_raw_all/1.5_2939a6548577025aef972e12d1d6c6d1.jpg	ffffe74347071f0d
+2024-03-30	abc	./data_raw_all/1.5_2ef5c79265d75feecdb1f209a37fde8b.jpg	ffff7c2107020301
+2024-03-30	abc	./data_raw_all/1.5_3a665e0fb853caa1686d11b1f9881f31.jpg	ffff7c2187020703
+2024-03-30	abc	./data_raw_all/1.5_5219ed6bf246bdb0c8a6272a6d4251c7.jpg	1f1f1103031f1f3f
+2024-03-30	abc	./data_raw_all/1.5_5aae8cb1d3d01a9ca9963a03632f25fd.jpg	fffff0c3c3425800
+2024-03-30	abc	./data_raw_all/1.5_5e35a75a8e8a82f0a8528cf45ffde56e.jpg	fffce0e1c0e2fcf5
+2024-03-30	abc	./data_raw_all/1.5_ana4_20220623-081159.jpg	ffff70a163370f17
+2024-03-30	abc	./data_raw_all/1.5_b4cef2d79a59bdf95148cb1ad78ead30.jpg	ffbf7c2387020303
+2024-03-30	abc	./data_raw_all/1.5_b5c49f6c1fd8559376bc2e618f5dad4c.jpg	3fff61c3e2f2f1e7
+2024-03-30	abc	./data_raw_all/1.5_ff05b180ffa721f56fb4362f7a21995f.jpg	fcfc0063f7f63480
+2024-03-30	abc	./data_raw_all/1.6_023d551a292f0f7f3b23bafb5944c961.jpg	ffbf7c2183020305
+2024-03-30	abc	./data_raw_all/1.6_04801c1476bdbb964650c2beb7eb644f.jpg	f9fef861612f1f0f
+2024-03-30	abc	./data_raw_all/1.6_0679_zeiger1_2020-06-15_17-03-25.jpg	f0f0f8e0e4f8e0c1
+2024-03-30	abc	./data_raw_all/1.6_0680_zeiger1_2020-06-15_17-13-42.jpg	f0f0f8f0e4f8c081
+2024-03-30	abc	./data_raw_all/1.6_0688_zeiger2_2019-11-19_18-07-04.jpg	ffffc183c5def8f0
+2024-03-30	abc	./data_raw_all/1.6_0692_zeiger2_2020-06-14_16-56-25.jpg	fdfcf8e0e0d8c080
+2024-03-30	abc	./data_raw_all/1.6_0705_zeiger4_2019-06-03T130009.jpg	feffc18103431f7d
+2024-03-30	abc	./data_raw_all/1.6_0762_zeiger4_2019-11-19_01-07-03.jpg	fffd4181e7ffdfff
+2024-03-30	abc	./data_raw_all/1.6_0eeb190c5c76df0b74cad1bec29d71a4.jpg	febf7d2187020309
+2024-03-30	abc	./data_raw_all/1.6_1775c78b8910c61178343a45e37e0cd2.jpg	f9fe7ce1412f1f1f
+2024-03-30	abc	./data_raw_all/1.6_19d9864da0fbc75a12fd1b394a5e5b78.jpg	fffdc00363723391
+2024-03-30	abc	./data_raw_all/1.6_3707359acf6a04c9d7aaf9122c7c4de0.jpg	ffffe0c1c3464001
+2024-03-30	abc	./data_raw_all/1.6_408f293cd00d9b00d19ab3ed964b0545.jpg	ffbf7d2183060b09
+2024-03-30	abc	./data_raw_all/1.6_5b3a4c496e5261a4b86e4b1edebfc6bd.jpg	ffffe10123470f2f
+2024-03-30	abc	./data_raw_all/1.6_67a424052619fc625b0086f6f7f7c437.jpg	fffff0e1e0e2d4d0
+2024-03-30	abc	./data_raw_all/1.6_99111392ed8e3342d779d0310f7471bb.jpg	fdfef0e1c1e0d0b4
+2024-03-30	abc	./data_raw_all/1.6_analog3_20200930-111543.jpg	ffff7f23271a0000
+2024-03-30	abc	./data_raw_all/1.6_dba0924086f044ef5fd4961ae34205c5.jpg	fcfe4061f7fe3680
+2024-03-30	abc	./data_raw_all/1.6_pointer_20211011-151241.jpg	ffbf9c80068080e0
+2024-03-30	abc	./data_raw_all/1.7_0675_analog1_20200817-071434.jpg	dfffe180c1e6edf7
+2024-03-30	abc	./data_raw_all/1.7_0761_zeiger3_2020-06-14_08-38-09.jpg	fffff9e3e75e0000
+2024-03-30	abc	./data_raw_all/1.7_1.8.jpg	fffffd8043220787
+2024-03-30	abc	./data_raw_all/1.7_15a4b91d8195f0694440c065c49f28d1.jpg	ffffe0c1c2e0fcb0
+2024-03-30	abc	./data_raw_all/1.7_1b7ec45bcc1681dca1fe4cb6f05af915.jpg	ffffe081e3e75f3f
+2024-03-30	abc	./data_raw_all/1.7_32327ed5ce30e4b79172ab569ec76ba8.jpg	fdfee0e1c060f4f4
+2024-03-30	abc	./data_raw_all/1.7_a61b7e6d7b078f92ba4f5b3cf5f63d43.jpg	ffcf8ea3a3c3c1e3
+2024-03-30	abc	./data_raw_all/1.7_dc849be23648ba86ecd99fdc647edefb.jpg	2f2f0b0103070f97
+2024-03-30	abc	./data_raw_all/1.7_eb2525024ea4ef2572626ab0ce97150a.jpg	ffff7081c3f76f3f
+2024-03-30	abc	./data_raw_all/1.8_03366c277d0481fbf258a13fb594cb33.jpg	b79f010103071f97
+2024-03-30	abc	./data_raw_all/1.8_0713_zeiger1_2019-06-01T161012.jpg	ffffc1e1c0c0f0b0
+2024-03-30	abc	./data_raw_all/1.8_0727_zeiger1_2019-06-04T235009.jpg	ffffc5a1c0c0c0b0
+2024-03-30	abc	./data_raw_all/1.8_0765_analog1_20200814-170323.jpg	d7ffe0c0c2e5fdf7
+2024-03-30	abc	./data_raw_all/1.8_0843e2dae35058e7ceaa9963e75b8aef.jpg	feff7080c1f76f3f
+2024-03-30	abc	./data_raw_all/1.8_0844_zeiger4_2019-11-19_15-32-04.jpg	ffff4181e3ffffff
+2024-03-30	abc	./data_raw_all/1.8_0892_zeiger4_2019-06-02T101009.jpg	fcffc381c3431f7f
+2024-03-30	abc	./data_raw_all/1.8_0bce9aebd6a4db61d23b46ad0723efc9.jpg	bfbf6f0107070b09
+2024-03-30	abc	./data_raw_all/1.8_14804e4d1d595f5bb44d926396d69387.jpg	f9fe7ee1612f1e1e
+2024-03-30	abc	./data_raw_all/1.8_22cae0da6ea3b4840332b9b6ae35b205.jpg	ffcfcf93a3cbc173
+2024-03-30	abc	./data_raw_all/1.8_274b3ae2c892ae90caa525cf0aef9b82.jpg	fdfee0c0e0f8e1e4
+2024-03-30	abc	./data_raw_all/1.8_29d2f19b0e55e8b73cb46eea5caed22e.jpg	f9fefee1612f1f1f
+2024-03-30	abc	./data_raw_all/1.8_466c3013bbd409b62633a51bc1cb3709.jpg	8e8ec1e1f7e7e3f3
+2024-03-30	abc	./data_raw_all/1.8_4f925c0e4f43f9d0a81744217ad779b4.jpg	fc3e4071f7fe3c80
+2024-03-30	abc	./data_raw_all/1.8_58a2749430db11088475594ae8374bf8.jpg	ffffe0e1c3425400
+2024-03-30	abc	./data_raw_all/1.8_58c60aab12f9e811d30540ea527bb181.jpg	ffcfcfa3a3c9c173
+2024-03-30	abc	./data_raw_all/1.8_59bd7dbc42300b2db72875b0cbe857fb.jpg	ffff600123478f27
+2024-03-30	abc	./data_raw_all/1.8_72b82dd7629e21713ba691c5445632a0.jpg	fdffe0c1c3c65a04
+2024-03-30	abc	./data_raw_all/1.8_75dd3145e3bdcb42663f4e448cf9d138.jpg	ffcfcea383c3c1f3
+2024-03-30	abc	./data_raw_all/1.8_ana3_20220624-200206.jpg	ffffc181e34ecb1c
+2024-03-30	abc	./data_raw_all/1.8_pointer_20211011-212054.jpg	ff9f9c80068480c0
+2024-03-30	abc	./data_raw_all/1.9_0850_analog3_20200814-014654.jpg	ffffe381c126c3f7
+2024-03-30	abc	./data_raw_all/1.9_0851_analog3_20200820-220133.jpg	ffffffc0c1e2cfd5
+2024-03-30	abc	./data_raw_all/1.9_0853_zeiger1_2019-06-05T044009.jpg	ffffc5c1c0c0c030
+2024-03-30	abc	./data_raw_all/1.9_0855_zeiger1_2020-06-14_14-18-59.jpg	f0f0f8e0e0d8c081
+2024-03-30	abc	./data_raw_all/1.9_0856_zeiger2_2019-09-15_05-49-06.jpg	7dffcfa1c342dfff
+2024-03-30	abc	./data_raw_all/1.9_0878_zeiger3_2019-09-14_20-25-52.jpg	ffffc8a1c343bfe7
+2024-03-30	abc	./data_raw_all/1.9_0879_zeiger3_2019-09-14_20-27-35.jpg	ffffdea1c142d7ff
+2024-03-30	abc	./data_raw_all/1.9_0890_zeiger3_2020-06-14_17-30-40.jpg	ffff7fe1e75e0000
+2024-03-30	abc	./data_raw_all/1.9_0891_zeiger3_2020-06-15_19-22-14.jpg	ffff7fe167580000
+2024-03-30	abc	./data_raw_all/1.9_0893_zeiger4_2019-06-02T103009.jpg	fbffc78103031b7d
+2024-03-30	abc	./data_raw_all/1.9_0936_zeiger3_2019-11-19_11-07-03.jpg	ffffc181e7dfc800
+2024-03-30	abc	./data_raw_all/1.9_0942_zeiger4_2020-04-29_11-35-02.jpg	fefee6e1e3e2dc15
+2024-03-30	abc	./data_raw_all/1.9_163c054ecef0640aa8221690d23c3f1f.jpg	fdfee0e0e0e2f4f5
+2024-03-30	abc	./data_raw_all/1.9_2d910ef1cac36ecfe9f1e1074bcf62ae.jpg	f7f7e0c0c1e6e7d6
+2024-03-30	abc	./data_raw_all/1.9_2fedd45745e60aeefa1f0cc95544ecd2.jpg	ffcf8ea3e2d2c1e3
+2024-03-30	abc	./data_raw_all/1.9_3eeea372ffbebd9bb931012f3cef1013.jpg	f7ffe0c0e1e2e7fe
+2024-03-30	abc	./data_raw_all/1.9_4ea27ae5911ec3b63ebf9e6274be92ce.jpg	ffcf9f3367780000
+2024-03-30	abc	./data_raw_all/1.9_513e961fe5d0dadbe7d3643a2a29e4f7.jpg	f8f8c0c0e0f8f8fc
+2024-03-30	abc	./data_raw_all/1.9_618471d0e44f6f3d0fdbe847aa974eaf.jpg	ffffc00163723385
+2024-03-30	abc	./data_raw_all/1.9_637a66ce10fe8a7e769dd5ee4d2c8ba6.jpg	fdffe0c1c0e2fcd0
+2024-03-30	abc	./data_raw_all/1.9_a19c8c9a4b56f6d37c39905f20895fa7.jpg	ffff7ea1c3420503
+2024-03-30	abc	./data_raw_all/1.9_a9a849b34826a5fb7b064598f3b31ea3.jpg	b79f050103079f17
+2024-03-30	abc	./data_raw_all/1.9_analog2_20201007-145724.jpg	fefcfce0e0d08080
+2024-03-30	abc	./data_raw_all/1.9_c0db9e456ac600f6e1573a647d343bfc.jpg	fbffe0e0c0e2fcfd
+2024-03-30	abc	./data_raw_all/2.0.jpg	1f3f6701c347bf7f
+2024-03-30	abc	./data_raw_all/2.0_0927_zeiger2_2020-04-29_12-32-02.jpg	ffffe6a0e1e290c0
+2024-03-30	abc	./data_raw_all/2.0_0930_zeiger3_2019-06-01T201013.jpg	ffffc681c1c0d1c0
+2024-03-30	abc	./data_raw_all/2.0_0931_zeiger3_2019-06-03T055009.jpg	ffffc681c1c080c0
+2024-03-30	abc	./data_raw_all/2.0_0940_zeiger4_2019-06-04T054009.jpg	feffc70101031b7d
+2024-03-30	abc	./data_raw_all/2.0_0947_analog2_20200819-164047.jpg	ffffe380c1a6c9d5
+2024-03-30	abc	./data_raw_all/2.0_1035_zeiger4_2019-06-04T051009.jpg	feffc78143431b7d
+2024-03-30	abc	./data_raw_all/2.0_23e9fa8f04bc9bb2599f9310a9766c5e.jpg	fdfff4a0c1e2d0b4
+2024-03-30	abc	./data_raw_all/2.0_3132d3a5d83bc6497d4fdecce78ef8a1.jpg	fdffe0e0c1e2f4f4
+2024-03-30	abc	./data_raw_all/2.0_444225bfd5643b7aca728301be586060.jpg	ffff70a0c1e76f3f
+2024-03-30	abc	./data_raw_all/2.0_5810d0ada4f0dffcaba7062461c3eded.jpg	fcfce0c0e0f8fcfc
+2024-03-30	abc	./data_raw_all/2.0_5d47b38e08fec2c5af7f98e3023603f5.jpg	ffff806163723785
+2024-03-30	abc	./data_raw_all/2.0_5f88ba4effbece36968e23aec1e4c49c.jpg	ffff402021470f27
+2024-03-30	abc	./data_raw_all/2.0_687ecce517e9b48893b4ed119b1094a6.jpg	f7ffe0c0c1e6eff6
+2024-03-30	abc	./data_raw_all/2.0_6e4a0c21bbc03e69a19a45a6cad4b083.jpg	8ecec3e1f7e7e3e7
+2024-03-30	abc	./data_raw_all/2.0_912bda4bf7b13166fdc618f46d57c36a.jpg	ffffc001234f8f2f
+2024-03-30	abc	./data_raw_all/2.0_952554eb27c0d7878cb77a6d789a77c9.jpg	f7ffe080c1e66fd6
+2024-03-30	abc	./data_raw_all/2.0_cb15144536516ee3bdac35286fd0bdd5.jpg	ffffe1e1e3fffc3e
+2024-03-30	abc	./data_raw_all/2.0_e75ee25092ad22fce1abd2d4289cc883.jpg	fefdf0e0e0f0d0d0
+2024-03-30	abc	./data_raw_all/2.0_pointer_20211008-173559.jpg	ff9f8e80068480e0
+2024-03-30	abc	./data_raw_all/2.1.jpg	ffff76e1c1429dd7
+2024-03-30	abc	./data_raw_all/2.1_0948_analog4_20200813-153909.jpg	bf7f4380a1efcff7
+2024-03-30	abc	./data_raw_all/2.1_0965_zeiger2_2019-06-02T132009.jpg	fcffe7e1c040c0c0
+2024-03-30	abc	./data_raw_all/2.1_1002_zeiger2_2019-06-05T051009.jpg	fdfee7c1c140c0c0
+2024-03-30	abc	./data_raw_all/2.1_1045_zeiger4_2020-04-29_14-11-01.jpg	fcfde6e1e3e2dc15
+2024-03-30	abc	./data_raw_all/2.1_1046_analog2_20200814-222202.jpg	ffffe380c0a2e1d7
+2024-03-30	abc	./data_raw_all/2.1_1093_zeiger4_2019-06-04T171009.jpg	feffc78101431b7f
+2024-03-30	abc	./data_raw_all/2.1_24c8c66855f5027c9ff4fd5c4f983ce8.jpg	fdffe4c0c1465004
+2024-03-30	abc	./data_raw_all/2.1_72812fcddecc8dbc2fd2aa20ce9a0b81.jpg	ffffe6c0c0e2fcb0
+2024-03-30	abc	./data_raw_all/2.1_7b517db3f6349feff6f36b8d45ed8769.jpg	ffffe380e1e77f3f
+2024-03-30	abc	./data_raw_all/2.1_ana1_20220629-220231.jpg	b7dfc0c0c0efd5f7
+2024-03-30	abc	./data_raw_all/2.1_ee404f2812e4b7d37ab339487ed423fa.jpg	dc5e6470f7fe3c80
+2024-03-30	abc	./data_raw_all/2.2.jpg	ffff8f2060270fcf
+2024-03-30	abc	./data_raw_all/2.2_09d07a491ca69e6ed7ae96f63a59b339.jpg	f7ffe781c1e66fd6
+2024-03-30	abc	./data_raw_all/2.2_0f1654d4f09db42e8414d51225910009.jpg	feff674181a79f17
+2024-03-30	abc	./data_raw_all/2.2_1004_zeiger2_2020-04-29_12-48-02.jpg	fffde6a0c0e290c0
+2024-03-30	abc	./data_raw_all/2.2_1032_zeiger3_2020-04-29_11-00-02.jpg	ffffe6c0c0429881
+2024-03-30	abc	./data_raw_all/2.2_1054_zeiger1_2019-06-01T174233.jpg	ffffe3e0c0c0f0b0
+2024-03-30	abc	./data_raw_all/2.2_1091_zeiger4_2019-06-03T052009.jpg	fefec78181431f7f
+2024-03-30	abc	./data_raw_all/2.2_1095_zeiger4_2019-11-19_00-27-02.jpg	ffff41a0e1dfbfff
+2024-03-30	abc	./data_raw_all/2.2_1096_zeiger4_2019-11-19_17-52-04.jpg	ffff41a0e1ffdfff
+2024-03-30	abc	./data_raw_all/2.2_1099_zeiger4_2020-04-29_12-32-02.jpg	f8fee6e1e1e2dc15
+2024-03-30	abc	./data_raw_all/2.2_10d71ce4d784da8bda8fb564118886b5.jpg	ffff4320214f8f6f
+2024-03-30	abc	./data_raw_all/2.2_1104_analog4_20200814-100802.jpg	bf3f4700a1cfcff7
+2024-03-30	abc	./data_raw_all/2.2_23070e7e1b8fc693a43d47db7985cf6c.jpg	f7fde1c1c0e7777d
+2024-03-30	abc	./data_raw_all/2.2_58b09e2fe292169319da6ed218fa5e1d.jpg	ffdf006061722585
+2024-03-30	abc	./data_raw_all/2.2_66954c743a801c20ea70babf69323ce3.jpg	f7fee7c0e0e2e77f
+2024-03-30	abc	./data_raw_all/2.2_75cc0e2e0c21cd7f06102ec3364a3f11.jpg	fdffe2e0c1e65a04
+2024-03-30	abc	./data_raw_all/2.2_80c56c32cdd05c7b448142c73f7eeb9e.jpg	ffffe6c0c1465801
+2024-03-30	abc	./data_raw_all/2.2_870cac6280d671dd72f15cf0b86f3192.jpg	ffffffa301000101
+2024-03-30	abc	./data_raw_all/2.2_9e85529d1f7508961cbb32eb6f735d92.jpg	ffcf9ff3637a8000
+2024-03-30	abc	./data_raw_all/2.2_analog3_20200925-060448.jpg	ffff7f21231e0000
+2024-03-30	abc	./data_raw_all/2.2_bd6dd3b125807a7bdba70b007a95b000.jpg	dc5e6670f3fe3e80
+2024-03-30	abc	./data_raw_all/2.2_pointer_20211007-172923.jpg	ff8f8e80008480e2
+2024-03-30	abc	./data_raw_all/2.3.jpg	ffff8f2060230fff
+2024-03-30	abc	./data_raw_all/2.3_1131_zeiger4_2019-06-01T161012.jpg	fbffc78101031f1f
+2024-03-30	abc	./data_raw_all/2.3_1137_zeiger4_2020-04-29_10-50-02.jpg	fcfcf6e1e1e2dc15
+2024-03-30	abc	./data_raw_all/2.3_1141_analog4_20200816-185815.jpg	3fbf4f008163dfef
+2024-03-30	abc	./data_raw_all/2.3_1cf0d4f151ee9105832edb4cdf4929d0.jpg	ffff4300214f8f27
+2024-03-30	abc	./data_raw_all/2.3_1e5e64228c7421e08667f1e56b70ed9e.jpg	f9fe7e60612f1f0f
+2024-03-30	abc	./data_raw_all/2.3_1eee6a86782e481956aee6606295eb00.jpg	fdfff6e0c0e2d4b4
+2024-03-30	abc	./data_raw_all/2.3_244f94acb4a21e87e4841774a17ae9e9.jpg	ffdf04606172278d
+2024-03-30	abc	./data_raw_all/2.3_29f54323964611316d18467e8cb42473.jpg	f7f7e781c0e667d6
+2024-03-30	abc	./data_raw_all/2.3_3dd959b94c068eea3d80d584b2060b58.jpg	fdffe7c0c1435004
+2024-03-30	abc	./data_raw_all/2.3_4cd7838798b0a1a656fa5c1c5267339c.jpg	ffc786b3e2f2c1e3
+2024-03-30	abc	./data_raw_all/2.3_525057225948a9c327d2496e4cc9bc81.jpg	c6c6c7e1d3e7e7e5
+2024-03-30	abc	./data_raw_all/2.3_a961f9b89c6c69715e50aaf17f444a61.jpg	ffc7f3f0f0c0c000
+2024-03-30	abc	./data_raw_all/2.3_ana4_20220623-070659.jpg	ffff63a0603f0f17
+2024-03-30	abc	./data_raw_all/2.3_b29e19970764a90c13b77e8f9216b5bb.jpg	ffffe761030f0f05
+2024-03-30	abc	./data_raw_all/2.3_ceaf88c823047e2f37599ada3bdf3f84.jpg	ffc7c6b3e3f2c061
+2024-03-30	abc	./data_raw_all/2.4_1139_analog1_20200814-194013.jpg	97fde3c0c0eff5f7
+2024-03-30	abc	./data_raw_all/2.4_1140_analog1_20200817-172714.jpg	dffdefc0c0e0edf5
+2024-03-30	abc	./data_raw_all/2.4_1152_zeiger3_2019-06-03T061009.jpg	ffffc780c0c080c0
+2024-03-30	abc	./data_raw_all/2.4_1175_zeiger4_2019-11-19_02-07-03.jpg	ffff43a0e0df9fff
+2024-03-30	abc	./data_raw_all/2.4_1206_zeiger4_2019-06-04T072009.jpg	f9ffc78141431b7d
+2024-03-30	abc	./data_raw_all/2.4_15124fcf98c1445f05adcfbbe478c9bc.jpg	3fff67c0e0f2f1e7
+2024-03-30	abc	./data_raw_all/2.4_1c0ac45dd1d802c649766e5266b4e092.jpg	fcfefee0e03e3c00
+2024-03-30	abc	./data_raw_all/2.4_2c85db36db22adeb94bab85c9f8b0855.jpg	ff8f06606072258d
+2024-03-30	abc	./data_raw_all/2.4_2f98c0ceaa6f0f720b6ed155ed9a5c4a.jpg	c4c7c7e1d3e7e7ed
+2024-03-30	abc	./data_raw_all/2.4_5de927916e47736d1e7b56af3f29280c.jpg	b79f470103071f17
+2024-03-30	abc	./data_raw_all/2.4_6384cc9aa9df9361d9a1df5fdc27c914.jpg	ffffefc0e0e0f0e0
+2024-03-30	abc	./data_raw_all/2.4_659d105478a8218795108bae1d2322f4.jpg	dc6e6670f2fe1c80
+2024-03-30	abc	./data_raw_all/2.4_a1498ec1e2e4d604871758cf51e23c11.jpg	ffff7fa1c1020d03
+2024-03-30	abc	./data_raw_all/2.4_pointer_20211008-201059.jpg	ef8f8e84008480e6
+2024-03-30	abc	./data_raw_all/2.5_079cf5d25858cad7cb83188986c0c397.jpg	ffffe6c0c0424000
+2024-03-30	abc	./data_raw_all/2.5_0b5199e0e354fbefb44cd22a340e166a.jpg	b79f070101071f97
+2024-03-30	abc	./data_raw_all/2.5_0e18c72ce90de10d204e5834caf9efe0.jpg	ffc7d6b3e3b3c071
+2024-03-30	abc	./data_raw_all/2.5_1228_zeiger4_2019-11-19_12-37-03.jpg	ffff43a0e0ffffff
+2024-03-30	abc	./data_raw_all/2.5_2.5.jpg	be3f6701c147ff7f
+2024-03-30	abc	./data_raw_all/2.5_2.6.jpg	ffff8f2020200fff
+2024-03-30	abc	./data_raw_all/2.5_2bcf5e3ebfa120ee24fa8d59ff22b2f3.jpg	fffff6e0c0e2dcd0
+2024-03-30	abc	./data_raw_all/2.5_2c1671a4f7e89d68d04a84d13a3f822a.jpg	fffff7e0c1425400
+2024-03-30	abc	./data_raw_all/2.5_2d42bd9e748320505d6e55d780f698b1.jpg	c4c6c7e1d1e7c7cd
+2024-03-30	abc	./data_raw_all/2.5_2f0b6991fad6e5308dd6bf5fffa0bede.jpg	e4e6c7e0d1e7c7cd
+2024-03-30	abc	./data_raw_all/2.5_376d515ad0375dbb701522c1e9a6a618.jpg	ffffe7e0e0fffc3e
+2024-03-30	abc	./data_raw_all/2.5_3ad3a97b9f0d5037d8a03e52a25ecf03.jpg	ffcfbf73637e8000
+2024-03-30	abc	./data_raw_all/2.5_4c1566da5b111cc6f623a7c50bc988d7.jpg	ff8f07606073279d
+2024-03-30	abc	./data_raw_all/2.5_4c2070149f964f340c89368a9e7b7ae5.jpg	ffc796e3e2f2c1f3
+2024-03-30	abc	./data_raw_all/2.5_4f8082a6699be53fbce2eecb3b4631a6.jpg	ffc7bf77633e8000
+2024-03-30	abc	./data_raw_all/2.5_521e1dae4c230c9f5a96a17d4abe8d09.jpg	ffc796e3e2b6c1e3
+2024-03-30	abc	./data_raw_all/2.5_74c2095b6c21afaba0de837a6fd2558f.jpg	f7f6e7c1e0e2e7fe
+2024-03-30	abc	./data_raw_all/2.5_analog3_20200926-214906.jpg	ffff7f27211e0000
+2024-03-30	abc	./data_raw_all/2.5_e4932b1d3335c5782adddd71dc8f3d56.jpg	ffffe741412f1f0d
+2024-03-30	abc	./data_raw_all/2.5_f9ddcc83fc7c113af51185445dae987c.jpg	feff67a0e0e36f3f
+2024-03-30	abc	./data_raw_all/2.5_main_ana3_20221213-123135.jpg	ffcf8f27232700c1
+2024-03-30	abc	./data_raw_all/2.6_1236_analog3_20200815-042431.jpg	ffffe7c1c0c0cbc5
+2024-03-30	abc	./data_raw_all/2.6_1e1287ecc7eb9b4cf62f442342a19816.jpg	ffc796e3e396c1f3
+2024-03-30	abc	./data_raw_all/2.6_2.7.jpg	ffff0f6000038fff
+2024-03-30	abc	./data_raw_all/2.6_2ad17a221a9b3b1af6c0e67030d941b7.jpg	ffffff0301000119
+2024-03-30	abc	./data_raw_all/2.6_35a8c7850fdd0293ac7a2b8e7fa354b9.jpg	ff0f676060630f9d
+2024-03-30	abc	./data_raw_all/2.6_3910269f764fc0dea1d50e276540f4a5.jpg	fdfff7e1c0e0dcb4
+2024-03-30	abc	./data_raw_all/2.6_3c778e291e176fe3f210bf02dec33251.jpg	ffffe780c0ef5f3f
+2024-03-30	abc	./data_raw_all/2.6_ana2_20220626-050213.jpg	ffffc781c142cbb4
+2024-03-30	abc	./data_raw_all/2.6_pointer_20211015-140414.jpg	e7878e84808c80e6
+2024-03-30	abc	./data_raw_all/2.7_1241_zeiger2_2019-06-04T053009.jpg	fdfee7e1c040d0c0
+2024-03-30	abc	./data_raw_all/2.7_12d090ef27e203342c871062c96e48ee.jpg	ffff472100430f27
+2024-03-30	abc	./data_raw_all/2.7_1304_zeiger4_2019-11-19_18-42-04.jpg	ffff47a1e0fbbfff
+2024-03-30	abc	./data_raw_all/2.7_1306_analog2_20200817-151940.jpg	ffffe780c080c9d5
+2024-03-30	abc	./data_raw_all/2.7_1317_zeiger2_2019-11-19_02-17-03.jpg	ffffcf81c1def8f0
+2024-03-30	abc	./data_raw_all/2.7_1325_zeiger3_2020-06-14_13-55-00.jpg	ffff7fe7e05e0000
+2024-03-30	abc	./data_raw_all/2.7_1366_zeiger4_2019-06-02T104009.jpg	fcffc78381431f7f
+2024-03-30	abc	./data_raw_all/2.7_44d5a6b56223f97269f9c1294a38875e.jpg	cc6e7670f0fe3c80
+2024-03-30	abc	./data_raw_all/2.7_a663d5902ac100ec24c5a05aa5d88dd8.jpg	f9fe7ee0602a1f1f
+2024-03-30	abc	./data_raw_all/2.7_ana3_20220629-152729.jpg	ffffe780c07fc514
+2024-03-30	abc	./data_raw_all/2.7_da175f26de0f7f07cd6236b2a28239c0.jpg	ffffe7a0c0e37f3f
+2024-03-30	abc	./data_raw_all/2.8.jpg	ff9f272100008fff
+2024-03-30	abc	./data_raw_all/2.8_072d1b6c07e33cafd28944fdbc739861.jpg	e6e6e7e3d1e7cfdd
+2024-03-30	abc	./data_raw_all/2.8_12356e26f312498540b90da56683713b.jpg	f7f5e5c3c0e7c6fd
+2024-03-30	abc	./data_raw_all/2.8_1367_zeiger4_2019-06-06T045009.jpg	f9ffc78301401f7d
+2024-03-30	abc	./data_raw_all/2.8_1a3e322cfec861e7b134512597db8b03.jpg	f7f7e581c0e067d6
+2024-03-30	abc	./data_raw_all/2.8_438af89d06cd9c63f95bbc4648ee1939.jpg	ffffe74100071f0d
+2024-03-30	abc	./data_raw_all/2.8_c30648d48510d5219756c3d9176c073e.jpg	e0e6e7e3d1e7cf9d
+2024-03-30	abc	./data_raw_all/2.8_d8a2111bc1603b2b30c38e88e2749049.jpg	ccee7670f0fe3e88
+2024-03-30	abc	./data_raw_all/2.8_pointer_20211006-194409.jpg	e7878686008c88ee
+2024-03-30	abc	./data_raw_all/2.9_1395_zeiger4_2020-04-29_14-30-02.jpg	fefce6e3e1e2dc15
+2024-03-30	abc	./data_raw_all/2.9_1a6dff25eaaa5a0e0f8f512c3a5c6f48.jpg	fdffe7c1c0405204
+2024-03-30	abc	./data_raw_all/2.9_2ad3dd7d058798612aef75f5f958534d.jpg	ffe7f1f0f0e0c000
+2024-03-30	abc	./data_raw_all/2.9_3.0.jpg	ffff67c3c040bfd7
+2024-03-30	abc	./data_raw_all/2.9_3521e1c41e98437be03a23eb5283fe1b.jpg	ffff672100500f27
+2024-03-30	abc	./data_raw_all/2.9_3dad68cbee6e9bbacba1dca664f35dff.jpg	9f0f676160620fdd
+2024-03-30	abc	./data_raw_all/2.9_631f52991691dc8e7abe69224d213192.jpg	ffff672120518f27
+2024-03-30	abc	./data_raw_all/2.9_a58b46c1b72020c5a0fd58874b16fe5c.jpg	ffc7d2e3a387c5f3
+2024-03-30	abc	./data_raw_all/2.9_c220532c07be380de72c46cb1d9afaef.jpg	b79f070301079f17
+2024-03-30	abc	./data_raw_all/2.9_c935920d63548bb1cf8f1785db97a57d.jpg	ffc7d3f3e393c171
+2024-03-30	abc	./data_raw_all/3.0_067369009f93093b28a7292a1179a8c2.jpg	979f070301051f17
+2024-03-30	abc	./data_raw_all/3.0_122f580aba4d76c12daf48c8809eebe1.jpg	fbffe2e1c0e0fcf1
+2024-03-30	abc	./data_raw_all/3.0_1396_analog4_20200822-052923.jpg	3fbf47238161dfef
+2024-03-30	abc	./data_raw_all/3.0_1471_zeiger3_2019-06-01T164011.jpg	ffffc781c040d1c0
+2024-03-30	abc	./data_raw_all/3.0_1485_zeiger3_2020-04-29_13-05-02.jpg	ffffe6c2c1409881
+2024-03-30	abc	./data_raw_all/3.0_1489_zeiger3_2020-06-16_16-32-32.jpg	ffffffe761580000
+2024-03-30	abc	./data_raw_all/3.0_1490_zeiger4_2019-06-03T161009.jpg	fbffc70301001b7d
+2024-03-30	abc	./data_raw_all/3.0_1520_zeiger4_2020-04-29_11-47-02.jpg	f8fee6e3e1e0de15
+2024-03-30	abc	./data_raw_all/3.0_1521_zeiger4_2020-04-29_12-02-11.jpg	fcfcf6e3e1e0de15
+2024-03-30	abc	./data_raw_all/3.0_1f763f4d8312d2a842e7adfa38458270.jpg	ffc7bf7763300000
+2024-03-30	abc	./data_raw_all/3.0_45cfe4d46001126f7a188f073db866d4.jpg	ffffe6c1e0e0fcd0
+2024-03-30	abc	./data_raw_all/3.0_604a94dcdf6175b2c8d9da2fd3dc4b2e.jpg	ffffe6e1c0405400
+2024-03-30	abc	./data_raw_all/3.0_66bcbf8d513b5e58e4e24753733de298.jpg	ffc7fff763348000
+2024-03-30	abc	./data_raw_all/3.0_787a72dfec2791256231366931fef601.jpg	e4767673e0fe3c80
+2024-03-30	abc	./data_raw_all/3.0_82a0845fa13ed81b21495264130dc6a7.jpg	ffff7ea7c1400107
+2024-03-30	abc	./data_raw_all/3.0_ana4_20220627-200221.jpg	ffff67a1201b0f17
+2024-03-30	abc	./data_raw_all/3.0_cce7712f8a40a6bdba645a22334c792d.jpg	ffc7fbf763328000
+2024-03-30	abc	./data_raw_all/3.0_ec2227062fae8051411745527befc6c4.jpg	ffc3d3e3e387c571
+2024-03-30	abc	./data_raw_all/3.1_0ca7959d3100d87457c77c236fb38f7d.jpg	ffdf5f0303000f05
+2024-03-30	abc	./data_raw_all/3.1_1389_zeiger3_2019-11-19_12-17-03.jpg	ffdfc783c1fb8a00
+2024-03-30	abc	./data_raw_all/3.1_1463_zeiger2_2020-04-29_12-02-11.jpg	fffde6a2e1e090c0
+2024-03-30	abc	./data_raw_all/3.1_1478_zeiger3_2019-11-19_11-22-03.jpg	ffdfc783e1fbc800
+2024-03-30	abc	./data_raw_all/3.1_1479_zeiger3_2019-11-19_12-07-03.jpg	ffffc783e1fbca80
+2024-03-30	abc	./data_raw_all/3.1_1497_zeiger4_2019-11-19_02-22-03.jpg	ffff47a3e1f09fff
+2024-03-30	abc	./data_raw_all/3.1_1544_zeiger2_2020-06-14_14-17-50.jpg	fcfcf8e4e0d0c080
+2024-03-30	abc	./data_raw_all/3.1_1585_zeiger4_2019-11-19_05-17-03.jpg	ffff47a3e1f1ffff
+2024-03-30	abc	./data_raw_all/3.1_1fc3f48ee05c53bec6062486f3f0dfdc.jpg	ffffe6c3c1405a00
+2024-03-30	abc	./data_raw_all/3.1_3.1.jpg	ff8f27230000dfff
+2024-03-30	abc	./data_raw_all/3.1_389098124e49cb30898dc8ebf44df61c.jpg	ffffe743010e0f07
+2024-03-30	abc	./data_raw_all/3.1_4d43d478b681127e070687bc91f93968.jpg	ffc3fb7f63308000
+2024-03-30	abc	./data_raw_all/3.1_4f3eb3ee64c843e0455ee32fe489ad01.jpg	f7f5e5c3c1e5477d
+2024-03-30	abc	./data_raw_all/3.1_5336b0c4e6b7962e96c361b6802ffd82.jpg	fff3f1f0f080c000
+2024-03-30	abc	./data_raw_all/3.1_692709121e9fbd3679df0180d12494aa.jpg	8f2767636000dffd
+2024-03-30	abc	./data_raw_all/3.1_75466d74f76ef982635ee446e1e5db19.jpg	feff674381219f07
+2024-03-30	abc	./data_raw_all/3.1_840dc5399d353667730859bf0c34d465.jpg	feff67a3c0f06f3f
+2024-03-30	abc	./data_raw_all/3.1_ana1_20220629-152229.jpg	b7dfc7c1c0f0c5f7
+2024-03-30	abc	./data_raw_all/3.1_ana4_20220622-200157.jpg	fffff7a161380f97
+2024-03-30	abc	./data_raw_all/3.1_bb553c01cfb39754137cec2bd112022f.jpg	ebffe6c0c0e0fcfd
+2024-03-30	abc	./data_raw_all/3.1_c397aa89e178c4b4f6c6bc480016a441.jpg	ffc3d2c38387c5f3
+2024-03-30	abc	./data_raw_all/3.1_c9694caec19e559c134a8b095e76746c.jpg	fcf8e4c0e0f0f8fc
+2024-03-30	abc	./data_raw_all/3.2_056a76cf267ff4dc55155e9edf11a236.jpg	ffff672301408f27
+2024-03-30	abc	./data_raw_all/3.2_065df20c964ca566c93b639795856dc6.jpg	bfbf670301010704
+2024-03-30	abc	./data_raw_all/3.2_0ea0b421c8c7281b99a11d2a7dba0bdf.jpg	c4767673e0fc3e80
+2024-03-30	abc	./data_raw_all/3.2_1524_analog1_20200818-065813 - Kopie.jpg	d7f5e382c1c0edf7
+2024-03-30	abc	./data_raw_all/3.2_1537_zeiger2_2019-06-01T174233.jpg	fdfee7c1c040f0e0
+2024-03-30	abc	./data_raw_all/3.2_1540_zeiger2_2019-09-14_11-40-12.jpg	7dffe783c140dfe7
+2024-03-30	abc	./data_raw_all/3.2_1592_analog1_20200814-233846.jpg	dffde382c1e0edff
+2024-03-30	abc	./data_raw_all/3.2_1599_zeiger1_2019-06-05T191009.jpg	ffffc7e3c0c0d0b0
+2024-03-30	abc	./data_raw_all/3.2_1637_zeiger4_2019-06-03T065009.jpg	fbff478701001b7d
+2024-03-30	abc	./data_raw_all/3.2_2da476516d9609f487cff67e1183622b.jpg	ffffe74341001f0d
+2024-03-30	abc	./data_raw_all/3.2_3.3.jpg	ff8f27230100fdff
+2024-03-30	abc	./data_raw_all/3.2_4904930dbce0bc29d32254e676022863.jpg	ffc3c3c38387c571
+2024-03-30	abc	./data_raw_all/3.2_87921cd0f30737bd1a68b82d78bdde9e.jpg	ff1f1f1f01009139
+2024-03-30	abc	./data_raw_all/3.2_8dd63757142f129d55fd1ceb73afd7b3.jpg	ffff6763011b0f03
+2024-03-30	abc	./data_raw_all/3.2_9180957235c2e902d14a25cad74cb8e7.jpg	fcfcf0e0e0f0f0d2
+2024-03-30	abc	./data_raw_all/3.2_a107362f1218a9ce1dcbc28d9319d3cb.jpg	ffffe76301020f0d
+2024-03-30	abc	./data_raw_all/3.2_a22dfadef716fce4a8bbf8023c3a8884.jpg	f9fefee160381617
+2024-03-30	abc	./data_raw_all/3.2_c8d2d8972042530b81474e264dcfdfbe.jpg	ffffe7e3e1fcfc3e
+2024-03-30	abc	./data_raw_all/3.2_e12f451f006fff76beec10cc0d21400a.jpg	f7fde5c3c0e0677d
+2024-03-30	abc	./data_raw_all/3.2_e445991cc18ab0fe9bb479af4f7e5d2a.jpg	8f2777636100fffd
+2024-03-30	abc	./data_raw_all/3.2_e4e8c242a94517b5e66fdec5baabedbe.jpg	ffffe7a3c1f16f3f
+2024-03-30	abc	./data_raw_all/3.2_ecfdf037e087ec51e63d21d53e9df60f.jpg	ffffeee0c0f0f0e0
+2024-03-30	abc	./data_raw_all/3.2_main_ana3_20221214-180121.jpg	ffc37b6763120000
+2024-03-30	abc	./data_raw_all/3.2_pointer_20211016-031403.jpg	e7838686008c98f6
+2024-03-30	abc	./data_raw_all/3.2_pointer_20211017-141026.jpg	e7838686808cd8fe
+2024-03-30	abc	./data_raw_all/3.3_0fd37303aeaa4b2f925f8aeffd48bbd1.jpg	fcf8e0e0e0f0c0e4
+2024-03-30	abc	./data_raw_all/3.3_1593_analog1_20200818-082608.jpg	d7f5e386c1e0e9f7
+2024-03-30	abc	./data_raw_all/3.3_1618_zeiger3_2019-06-01T165011.jpg	ffffc781c14090c0
+2024-03-30	abc	./data_raw_all/3.3_1623_zeiger3_2019-06-01T174233.jpg	ffffc783c1c0d0c0
+2024-03-30	abc	./data_raw_all/3.3_1646_zeiger4_2020-04-29_12-15-02.jpg	fcffe6e3e1e0dc15
+2024-03-30	abc	./data_raw_all/3.3_1695_zeiger4_2019-09-14_23-00-13.jpg	f9ff2f87c141ffff
+2024-03-30	abc	./data_raw_all/3.3_1698_zeiger4_2019-11-19_01-57-03.jpg	ffff6783e1f19fff
+2024-03-30	abc	./data_raw_all/3.3_255a032aa7766769794395f27dc8b42b.jpg	fcfe7e27c140ddb7
+2024-03-30	abc	./data_raw_all/3.3_310ff9516f75b8caa682d66a067a09b8.jpg	fffff6e3c0e0fcf0
+2024-03-30	abc	./data_raw_all/3.3_3980a674547f16d77fb356a3f0df8fde.jpg	f7ffe5c3c1e0e77e
+2024-03-30	abc	./data_raw_all/3.3_analog3_20201001-062503.jpg	ffff7f2723180000
+2024-03-30	abc	./data_raw_all/3.3_b6c8d6d745cb8d076b052f9fbc7f8ad7.jpg	f8f2e7e3d3c19f3d
+2024-03-30	abc	./data_raw_all/3.3_d10c96df85965a79954935f2b4a1e077.jpg	ffff6f6301100f07
+2024-03-30	abc	./data_raw_all/3.3_d6b7dccadc4cc9f753bb140db2c2a0a5.jpg	b79f470303011f17
+2024-03-30	abc	./data_raw_all/3.3_deb59dd19c8a3f5b349510e3acc49663.jpg	ffc3d3a38387cdf3
+2024-03-30	abc	./data_raw_all/3.3_ed15a808f8ca200d417b948858e84f10.jpg	c0767673e1fc3e88
+2024-03-30	abc	./data_raw_all/3.4.jpg	be7f6723c140ff7f
+2024-03-30	abc	./data_raw_all/3.4_039747db981345b6cec23e356acc60c5.jpg	ecfcfea6c240f9bf
+2024-03-30	abc	./data_raw_all/3.4_0e7fe6e926d86a91b993297affde8261.jpg	f7ffe583c3e067d6
+2024-03-30	abc	./data_raw_all/3.4_114824fbeb652d9b0e9b98f9129ad5bd.jpg	ffdf7f0303010d05
+2024-03-30	abc	./data_raw_all/3.4_1648_analog2_20200815-235143.jpg	ffffe786c120c9d5
+2024-03-30	abc	./data_raw_all/3.4_1679_zeiger3_2019-11-19_08-22-03.jpg	ffdfc787e1f3c880
+2024-03-30	abc	./data_raw_all/3.4_1689_zeiger3_2019-11-19_09-32-03.jpg	ffdfc787e1d38800
+2024-03-30	abc	./data_raw_all/3.4_1720_zeiger4_2019-06-03T051009.jpg	fcfec787c1411b7f
+2024-03-30	abc	./data_raw_all/3.4_1721_zeiger4_2019-06-04T075009.jpg	feffc78701001b7d
+2024-03-30	abc	./data_raw_all/3.4_1736_analog4_20200813-195537.jpg	bf3f4703a1f1cff7
+2024-03-30	abc	./data_raw_all/3.4_1788_zeiger2_2019-11-19_01-12-03.jpg	ffffcf87c3f0f8e0
+2024-03-30	abc	./data_raw_all/3.4_99fe587bcb55a97d7ff0016222a7abb8.jpg	f0767673e1f83e88
+2024-03-30	abc	./data_raw_all/3.4_bb2454a9079fb538291cb22e4a1294ad.jpg	8f3777636100fcff
+2024-03-30	abc	./data_raw_all/3.4_f457305f6cb8f2a6fc4a543ddafbcb7c.jpg	ecbe7ea6c240f9bf
+2024-03-30	abc	./data_raw_all/3.4_fcec2f45a2c851e040125be766615383.jpg	fcfe7ea6c240ddbf
+2024-03-30	abc	./data_raw_all/3.4_pointer_20211014-221029.jpg	e781828682989cf6
+2024-03-30	abc	./data_raw_all/3.5.jpg	cf8f37230180fdff
+2024-03-30	abc	./data_raw_all/3.5_0bf3b9835f75a87ec45b50b56b911761.jpg	f9fe7ee16128171f
+2024-03-30	abc	./data_raw_all/3.5_1646244529cc4088ec502f2de1c901af.jpg	ff0f1f170180933b
+2024-03-30	abc	./data_raw_all/3.5_1700_analog1_20200812-230442 - Kopie.jpg	d7fde7c2c0e1e5ff
+2024-03-30	abc	./data_raw_all/3.5_1701_analog1_20200815-023748.jpg	dfffe1c6c1e0e1ff
+2024-03-30	abc	./data_raw_all/3.5_1732_zeiger4_2020-04-29_14-41-02.jpg	fefee6e3e3e0dc11
+2024-03-30	abc	./data_raw_all/3.5_1737_analog4_20200814-141641.jpg	bf7f470381f1cdf7
+2024-03-30	abc	./data_raw_all/3.5_1786_zeiger1_2020-06-14_17-14-51.jpg	f0f0f8e4e0f8c0c1
+2024-03-30	abc	./data_raw_all/3.5_1787_zeiger2_2019-09-15_06-20-12.jpg	7dffcfa3c141d5ff
+2024-03-30	abc	./data_raw_all/3.5_1795_zeiger4_2019-06-01T165011.jpg	f9ffc78701411d1f
+2024-03-30	abc	./data_raw_all/3.5_1807_zeiger4_2019-06-05T043009.jpg	fcffc78783411b7f
+2024-03-30	abc	./data_raw_all/3.5_1808_zeiger4_2019-06-06T155009.jpg	fbffc7070301197f
+2024-03-30	abc	./data_raw_all/3.5_2627c7a57c1b0efb0669ddf19ae7ef76.jpg	ffff7f2703000103
+2024-03-30	abc	./data_raw_all/3.5_2c82b3a7265760a8750bd973212a4486.jpg	ecfc7e26c240c9bf
+2024-03-30	abc	./data_raw_all/3.5_3.6.jpg	ffff6fc7c340b9bf
+2024-03-30	abc	./data_raw_all/3.5_3b5a7b86bac43cc225fb84ddbf95d3f4.jpg	fffff76301011f07
+2024-03-30	abc	./data_raw_all/3.5_4a43ff3dd7a6366069124b80cf089213.jpg	fcfefee6e2383c00
+2024-03-30	abc	./data_raw_all/3.5_85f369b634657ed9bd567d354b85230b.jpg	ff1f1f1701809319
+2024-03-30	abc	./data_raw_all/3.5_ana2_20220624-090204.jpg	ffffcf858140c9a4
+2024-03-30	abc	./data_raw_all/3.5_c6025c3fe574a55332c8c1a789774177.jpg	ffffe74341211e0d
+2024-03-30	abc	./data_raw_all/3.5_f27d67e7b9ddf1b725cae6180fc83b58.jpg	f7fee5c3c1f0a7fe
+2024-03-30	abc	./data_raw_all/3.6_03c6114abf229bf6c8400fb6ee21d8ba.jpg	fcfc7ea6c240d1bf
+2024-03-30	abc	./data_raw_all/3.6_1821_zeiger4_2019-06-04T104010.jpg	feffc7870301197f
+2024-03-30	abc	./data_raw_all/3.6_1d9ac015c8d0d235c44b56f055122fe1.jpg	fffff6e3c1405001
+2024-03-30	abc	./data_raw_all/3.6_4e3bead06d3e609a73c7efc97ebd35f4.jpg	ff1f1f170700d339
+2024-03-30	abc	./data_raw_all/3.6_533d85efe2d02650c68779e48875774d.jpg	ff1f0f070790b3bb
+2024-03-30	abc	./data_raw_all/3.6_6148aceb40393a66a22df4331ced0755.jpg	ffdf5f0303010904
+2024-03-30	abc	./data_raw_all/3.6_80d41586e868bdbd138a0c7e8d37d421.jpg	ffff670321710127
+2024-03-30	abc	./data_raw_all/3.6_8f2e64bda3748d47c667c72bb0fb0459.jpg	8737776361c0fcff
+2024-03-30	abc	./data_raw_all/3.6_9eee6d93a9e275a657f7fada0817f53e.jpg	ffffe6e1c1e0d4d0
+2024-03-30	abc	./data_raw_all/3.6_ana4_20220629-161729.jpg	ffff77a361390d97
+2024-03-30	abc	./data_raw_all/3.6_b4269fab24db96287fc58173ce3398c9.jpg	ff0f1f1f0100d339
+2024-03-30	abc	./data_raw_all/3.6_b614d79a5065afeb2fabe4c0bc5ce62b.jpg	ffff7783c1f14d3f
+2024-03-30	abc	./data_raw_all/3.6_ce9b927d27ad87faceb79f768f36d168.jpg	fcbcfe26c240c1bd
+2024-03-30	abc	./data_raw_all/3.6_d8c7f1c1da9f76a208e72cd64810a9b5.jpg	d07e7673e3f83c80
+2024-03-30	abc	./data_raw_all/3.6_fa456d343ceeb4a2c85494ce161ef195.jpg	f8f8f3e3f3b11d3d
+2024-03-30	abc	./data_raw_all/3.6_pointer_20211011-091850.jpg	e78181868298b8fe
+2024-03-30	abc	./data_raw_all/3.7_1814_analog1_20200821-173148.jpg	dffde386c3e0e1ff
+2024-03-30	abc	./data_raw_all/3.7_1824_zeiger4_2019-06-06T185009.jpg	f9ffc7870341197f
+2024-03-30	abc	./data_raw_all/3.7_1880_zeiger3_2019-09-15_06-00-12.jpg	ffff5ea3c341d1ff
+2024-03-30	abc	./data_raw_all/3.7_1882_zeiger3_2020-06-14_17-03-17.jpg	ffff7fe7e7500000
+2024-03-30	abc	./data_raw_all/3.7_3.7.jpg	cf8737230381f9ff
+2024-03-30	abc	./data_raw_all/3.7_3.8.jpg	fcfcfce0c0e0f8f8
+2024-03-30	abc	./data_raw_all/3.7_32b3c2109df9d4ba621e46486d9b58bd.jpg	979f070303011d97
+2024-03-30	abc	./data_raw_all/3.7_58b4064617caa6231581197351fbe557.jpg	fcbc7e26c242d1bd
+2024-03-30	abc	./data_raw_all/3.7_6e8991334057c57234600a07a5d7e857.jpg	ff1f0f070790d33f
+2024-03-30	abc	./data_raw_all/3.7_99c027da533fcba7a9eb7f1c83500759.jpg	ffe3c1b38387cd71
+2024-03-30	abc	./data_raw_all/3.7_ana3_20220817-100931.jpg	fefbc9a5c0c0d0ff
+2024-03-30	abc	./data_raw_all/3.7_d3eca20aa56dead4e8cf61a2e7d83a9c.jpg	ffffe76303110d07
+2024-03-30	abc	./data_raw_all/3.7_dba27bce08ce2eb98561e55b122631d0.jpg	fff3fb7f63320000
+2024-03-30	abc	./data_raw_all/3.7_main_ana3_20221213-123635.jpg	ffe7f347270701e1
+2024-03-30	abc	./data_raw_all/3.7_main_ana3_20221214-193621.jpg	fff37b6323020000
+2024-03-30	abc	./data_raw_all/3.7_pointer_20211011-123027.jpg	e38180868298b8f6
+2024-03-30	abc	./data_raw_all/3.8_0d6ca6e20653e3a2c87e08a43a06a3cc.jpg	ffffe783c3f14d3f
+2024-03-30	abc	./data_raw_all/3.8_157e6c33abee9facbff527eb49e41377.jpg	ffe3c1818387cd71
+2024-03-30	abc	./data_raw_all/3.8_1735_analog3_20200817-073358.jpg	fffff3e7c3a0c1c5
+2024-03-30	abc	./data_raw_all/3.8_1881_zeiger3_2020-04-29_14-10-02.jpg	ffffe6c2c2409081
+2024-03-30	abc	./data_raw_all/3.8_1884_zeiger4_2019-06-04T110009.jpg	feffc7874341197d
+2024-03-30	abc	./data_raw_all/3.8_1897_analog1_20200815-075026.jpg	dfffe3c6c2e0e1ff
+2024-03-30	abc	./data_raw_all/3.8_3c3bb7b5bfedbcbe15c4a8ce81aff368.jpg	fcfcfe26c242d1b9
+2024-03-30	abc	./data_raw_all/3.8_47511cc27350d70896ac0bcacc4ed834.jpg	bfbf670303030904
+2024-03-30	abc	./data_raw_all/3.8_48a2247fb4f9a1f90920c9c9c4dcdb91.jpg	b79f070303039d17
+2024-03-30	abc	./data_raw_all/3.8_5493b246e96582d18cfd41376d9d0ff0.jpg	d0fe76f3e2f83c18
+2024-03-30	abc	./data_raw_all/3.8_5628be589c6e2217537a96b9df6ed6a3.jpg	fcf8f3f3f3b3193d
+2024-03-30	abc	./data_raw_all/3.8_745435a45a668887d9391d8efdd8d4be.jpg	8733776301c0fcff
+2024-03-30	abc	./data_raw_all/3.8_b07399f4ae5e7497097443d55a71b3e4.jpg	ff0f0f070792db3f
+2024-03-30	abc	./data_raw_all/3.8_b865f38fb9e3daa0060cab371f97c414.jpg	feff77a3c1f1693f
+2024-03-30	abc	./data_raw_all/3.8_c477c74d90b97e8b7fe8b213b81e677c.jpg	ffffeec4c0e0f0a0
+2024-03-30	abc	./data_raw_all/3.8_d8361bfca336b28adeb65f545f2e7271.jpg	f7f5e5c3c3e3c6f5
+2024-03-30	abc	./data_raw_all/3.9.jpg	cf97332303c1f9ff
+2024-03-30	abc	./data_raw_all/3.9_0991882a767a8e9b2357d4047177e5dc.jpg	8333736383c1fdff
+2024-03-30	abc	./data_raw_all/3.9_0d0eb7f9c4aa7e6e1474a38f4359ae64.jpg	f9fefee161301f07
+2024-03-30	abc	./data_raw_all/3.9_1896_analog1_20200813-040004.jpg	d7fde7c2c2e1e9ff
+2024-03-30	abc	./data_raw_all/3.9_1899_analog1_20200815-083117.jpg	d7fde182c2e0e1ff
+2024-03-30	abc	./data_raw_all/3.9_1901_analog2_20200817-163312.jpg	ffffe786c3a0c1d5
+2024-03-30	abc	./data_raw_all/3.9_1904_analog4_20200820-001616.jpg	3fbf47078361d1ef
+2024-03-30	abc	./data_raw_all/3.9_1942_analog3_20200815-205535.jpg	fffff7c783a3c1c1
+2024-03-30	abc	./data_raw_all/3.9_1970_zeiger2_2019-11-19_18-32-04.jpg	ffffcf87c7f2f8f0
+2024-03-30	abc	./data_raw_all/3.9_2027_zeiger4_2019-11-19_18-17-04.jpg	ffff4783e3f39bff
+2024-03-30	abc	./data_raw_all/3.9_22475cfca71696e06df40c925063cb52.jpg	379f070303031b97
+2024-03-30	abc	./data_raw_all/3.9_4.0.jpg	cf93332282c1f9ff
+2024-03-30	abc	./data_raw_all/3.9_586cbd728968d79cecec23052196684b.jpg	ffe3c1a1838fdde3
+2024-03-30	abc	./data_raw_all/3.9_5ffa125223b532fdf40bc2a7188f712a.jpg	ffffe7430303190d
+2024-03-30	abc	./data_raw_all/3.9_64a0f2631a1d2e38e6aff976c9dce018.jpg	ffffe6c3c0e0f0b0
+2024-03-30	abc	./data_raw_all/3.9_81660a87054180833bf23cad814527ef.jpg	f87a7e73e3fa3c80
+2024-03-30	abc	./data_raw_all/3.9_9c3d37bcbc2eeeaf3ce68359dbefd022.jpg	fff3f97d63100000
+2024-03-30	abc	./data_raw_all/3.9_acc6f94bacf4271ff1b97ecc18e2556e.jpg	f7f7e583c3e2e3d6
+2024-03-30	abc	./data_raw_all/3.9_ana3_20220629-153729.jpg	ffffe783e171c114
+2024-03-30	abc	./data_raw_all/3.9_ana4_20220627-002717.jpg	ffff678321110907
+2024-03-30	abc	./data_raw_all/3.9_main_ana3_20221213-124105.jpg	fff7fb03070711c1
+2024-03-30	abc	./data_raw_all/4.0_0074c6a84d18db308021594ff9419062.jpg	ffff670323430107
+2024-03-30	abc	./data_raw_all/4.0_032068e1fae4132c724a26ed3091cdb3.jpg	fcfae0c0e0f0f0fc
+2024-03-30	abc	./data_raw_all/4.0_095bc086caee657c5e31e8502b33fc8d.jpg	ff0f0f070780d2bf
+2024-03-30	abc	./data_raw_all/4.0_1984_zeiger3_2019-11-19_09-42-03.jpg	ffffc787e3d3c800
+2024-03-30	abc	./data_raw_all/4.0_1986_zeiger3_2019-11-19_09-52-03.jpg	ffffc787e7d38a00
+2024-03-30	abc	./data_raw_all/4.0_1990_zeiger4_2019-06-01T190020.jpg	ffffc7830303190d
+2024-03-30	abc	./data_raw_all/4.0_1997_zeiger4_2019-06-01T204131.jpg	feffc7870343191d
+2024-03-30	abc	./data_raw_all/4.0_1998_zeiger4_2019-06-02T075009.jpg	f9ffc7870303197d
+2024-03-30	abc	./data_raw_all/4.0_2000_zeiger4_2019-06-03T112009.jpg	feffc78703031979
+2024-03-30	abc	./data_raw_all/4.0_2003_zeiger4_2019-06-04T210009.jpg	f9ff470703031969
+2024-03-30	abc	./data_raw_all/4.0_2022_zeiger4_2019-06-05T174009.jpg	fcffc7878343197d
+2024-03-30	abc	./data_raw_all/4.0_20ac3116a1a259d549f16406c8884fc4.jpg	c0787a73e3fa3c80
+2024-03-30	abc	./data_raw_all/4.0_22708f2f193ca47aa150e3e767f56d12.jpg	fcfcf1f3f3a31b3d
+2024-03-30	abc	./data_raw_all/4.0_2304026bc2766a96beb2cc574033797e.jpg	feff676383a39917
+2024-03-30	abc	./data_raw_all/4.0_310bbe01005c4539dbb63ed47b30bc34.jpg	ff9f5f0303030105
+2024-03-30	abc	./data_raw_all/4.0_4.1.jpg	c793332282e0f9ff
+2024-03-30	abc	./data_raw_all/4.0_419b104a69f39a3c177eb9b8ad55515a.jpg	fffbf9f0a080c000
+2024-03-30	abc	./data_raw_all/4.0_5d86c314c47968188e0b384dfd426dc5.jpg	ffdf7f0303030900
+2024-03-30	abc	./data_raw_all/4.0_69f38954f10856b8667536ec29258fee.jpg	ffffe6c3c3404101
+2024-03-30	abc	./data_raw_all/4.0_ana4_20220629-154229.jpg	fffff3a361310997
+2024-03-30	abc	./data_raw_all/4.0_c6e32c467cf2e51b2a06110a34db7441.jpg	fdfae4c0e0f0e1a4
+2024-03-30	abc	./data_raw_all/4.0_da1d0cf843208372478636a2320bd6c7.jpg	ffff7f6303130907
+2024-03-30	abc	./data_raw_all/4.0_ebb9add2092397fb30e957c3eb01654a.jpg	833b736383e1f9ff
+2024-03-30	abc	./data_raw_all/4.0_ec351329dbea0c7272d52b7badc9ddc1.jpg	ffff7383c3f1693f
+2024-03-30	abc	./data_raw_all/4.0_pointer_20211009-232112.jpg	e781808286b0f8fe
+2024-03-30	abc	./data_raw_all/4.1_2042_zeiger2_2019-09-14_19-50-12.jpg	7dffe7a3c343d9f7
+2024-03-30	abc	./data_raw_all/4.1_2045_zeiger2_2019-09-14_20-20-13.jpg	7cffe7a34143d9f7
+2024-03-30	abc	./data_raw_all/4.1_2047_zeiger2_2019-09-14_20-27-35.jpg	7cfee7a3e143d1fd
+2024-03-30	abc	./data_raw_all/4.1_2049_zeiger2_2019-09-14_20-30-29.jpg	7dffcfa3c342d3fb
+2024-03-30	abc	./data_raw_all/4.1_2111_zeiger3_2019-11-19_01-07-03.jpg	ffffc787e7f3d880
+2024-03-30	abc	./data_raw_all/4.1_2118_zeiger4_2019-06-01T203011.jpg	f9ffc78703431b1d
+2024-03-30	abc	./data_raw_all/4.1_2120_zeiger4_2019-06-03T171009.jpg	f9ffc78703031b69
+2024-03-30	abc	./data_raw_all/4.1_2124_zeiger4_2020-04-29_11-28-02.jpg	f8fee6e3e3e2d015
+2024-03-30	abc	./data_raw_all/4.1_2125_zeiger4_2020-04-29_12-44-02.jpg	fcfce6e3e3e2d215
+2024-03-30	abc	./data_raw_all/4.1_2130_analog2_20200816-042447.jpg	ffffe786c322c1d1
+2024-03-30	abc	./data_raw_all/4.1_2fc93b2548d98fcb2ff0d2e220bcdbcd.jpg	7cfef9f3f323133d
+2024-03-30	abc	./data_raw_all/4.1_3561d70f515be5926e1c95dcabd63a20.jpg	f9fefee161301007
+2024-03-30	abc	./data_raw_all/4.1_3b3221bd044fba923da306576ac58b9b.jpg	fcbc7e26c642c3b3
+2024-03-30	abc	./data_raw_all/4.1_3cb0af641b87bfef71e2bb8d3126e00f.jpg	fdfefee36120101f
+2024-03-30	abc	./data_raw_all/4.1_4.2.jpg	9f3f67034343b37b
+2024-03-30	abc	./data_raw_all/4.1_4e0b56d4b2094d70184b0e44d27f110c.jpg	ffdf5f2303030301
+2024-03-30	abc	./data_raw_all/4.1_4ef5fecd8cabde2e47af97e5bf581f12.jpg	fdffe7c3c3615000
+2024-03-30	abc	./data_raw_all/4.1_8a1b2a2e8cbc801d7f04701d55df3e29.jpg	fcbc7ea6c242d3bb
+2024-03-30	abc	./data_raw_all/4.1_98335b9fc961e02454519c2ac5897d2a.jpg	d8787a73e3f23880
+2024-03-30	abc	./data_raw_all/4.1_a8443d14f892e4acc7b6786b173b33f1.jpg	f7fde5c3c3e3527d
+2024-03-30	abc	./data_raw_all/4.1_dbb12a72a7aa78d8694425e75a39a641.jpg	ffff672323438323
+2024-03-30	abc	./data_raw_all/4.1_e97a247ed6838f7de069fc5fdf8e0b23.jpg	ffe3c18183c3fd73
+2024-03-30	abc	./data_raw_all/4.1_main_ana3_20221214-192121.jpg	fff3f92103079300
+2024-03-30	abc	./data_raw_all/4.2_1226edadff5a24797464771b148eaadc.jpg	833973a3c3e3f1f9
+2024-03-30	abc	./data_raw_all/4.2_17849fdd3be0ca6a4d2284a6616079f0.jpg	fdffe6c1c1e0d0b8
+2024-03-30	abc	./data_raw_all/4.2_2032_analog4_20200813-105014.jpg	bf7f4703a3d3c3f7
+2024-03-30	abc	./data_raw_all/4.2_2112_zeiger3_2019-11-19_02-07-03.jpg	ffffc787e7d3d000
+2024-03-30	abc	./data_raw_all/4.2_2127_zeiger4_2020-04-29_13-22-02.jpg	fefce6e3e3e2d011
+2024-03-30	abc	./data_raw_all/4.2_2162_zeiger4_2019-06-06T093009.jpg	feffc70703031369
+2024-03-30	abc	./data_raw_all/4.2_2188_zeiger4_2019-11-19_01-47-03.jpg	ffff47a3e3f3d3ff
+2024-03-30	abc	./data_raw_all/4.2_3ea119aaca1b4d047b836e27fd3ea0c3.jpg	fcfc7ea6c642c3b1
+2024-03-30	abc	./data_raw_all/4.2_4694a8dc029f10c88455f1d2dc7e1bc0.jpg	fdfee2e1c1e0f0fc
+2024-03-30	abc	./data_raw_all/4.2_4c28c2f4b3ba9368185e84664fa3fbef.jpg	b79f070303031317
+2024-03-30	abc	./data_raw_all/4.2_5eaa8556ef1ec19beca3437174ed3d76.jpg	8f8f07878792d3bf
+2024-03-30	abc	./data_raw_all/4.2_78baee45e2d30eb6d113f63aa9f2b518.jpg	fdffe7c3c3c25000
+2024-03-30	abc	./data_raw_all/4.2_a23a9fb39bfaf7e6cae2fca776f0128a.jpg	1f1f070303131b3f
+2024-03-30	abc	./data_raw_all/4.2_e503476b892e37a2a67ef49bd826d2d4.jpg	ffffe783e3e3413f
+2024-03-30	abc	./data_raw_all/4.2_eae454f54a7795ae3c99f2ce907984ab.jpg	f7ffe1c3e1f2e37e
+2024-03-30	abc	./data_raw_all/4.2_f9dc08617d41ddbfd4609096320a422d.jpg	f7ffe583c3e26356
+2024-03-30	abc	./data_raw_all/4.2_pointer_20211010-103636.jpg	e781808006f0f8f8
+2024-03-30	abc	./data_raw_all/4.2_pointer_20211010-104009.jpg	e781808006f0fafe
+2024-03-30	abc	./data_raw_all/4.3_0879f49ebff896155e2794b314e74dee.jpg	fcfc7e26c642e3f3
+2024-03-30	abc	./data_raw_all/4.3_2129_analog1_20200818-183028.jpg	d7fde386c3e2e1fd
+2024-03-30	abc	./data_raw_all/4.3_2131_analog3_20200817-114837.jpg	fffff3c7c3e2c3d1
+2024-03-30	abc	./data_raw_all/4.3_2140_zeiger2_2019-09-14_12-40-12.jpg	7dffe7a3c343d3ef
+2024-03-30	abc	./data_raw_all/4.3_2160_zeiger4_2019-06-04T172009.jpg	fcffc787c3431379
+2024-03-30	abc	./data_raw_all/4.3_2fad4056768f5d4dce52daa761b7e6db.jpg	feff7ba3e3f3613f
+2024-03-30	abc	./data_raw_all/4.3_35e6478a21e953d9ee5de53b14b72f18.jpg	fffff383e3f3613f
+2024-03-30	abc	./data_raw_all/4.3_4.4.jpg	c7839ba082e2f1fb
+2024-03-30	abc	./data_raw_all/4.3_437d041fc824e644aedf6aa70e73606f.jpg	fbffe2c0c0e2f0f9
+2024-03-30	abc	./data_raw_all/4.3_5b9e538c19a684aa8167a846abdd5441.jpg	ff9f7f0303030300
+2024-03-30	abc	./data_raw_all/4.3_7cb0371638e9a555e23badfaed47c813.jpg	cf8f87878782d33f
+2024-03-30	abc	./data_raw_all/4.3_87d8bc066ea187126ff2470938b9bbdc.jpg	d87c7a63e3f23a80
+2024-03-30	abc	./data_raw_all/4.3_9cdccaf04f5ed86f2033e9ad790b5307.jpg	cf8f0f878783d33f
+2024-03-30	abc	./data_raw_all/4.3_aedf0c3a941e3b7aeb0ad2924b3ff60a.jpg	ffffe7434323130d
+2024-03-30	abc	./data_raw_all/4.3_analog1_20200928-200357.jpg	f0f0f8f0e0f0c0c0
+2024-03-30	abc	./data_raw_all/4.3_ccd00adc5fa25d72c68a03b857ff46be.jpg	ffff7383e3f3533f
+2024-03-30	abc	./data_raw_all/4.3_d7ab47d17fb9d37003becb60ff8376d8.jpg	ffffe6e3c2e2f0f8
+2024-03-30	abc	./data_raw_all/4.4_014ba9ebbf1905cd0dd7a01fdd259519.jpg	f7ffe1c3e3e2e35a
+2024-03-30	abc	./data_raw_all/4.4_0b0199327533c7ef1e3d292d325f7e80.jpg	8f8f0f878780d3bf
+2024-03-30	abc	./data_raw_all/4.4_102ca879129cadda1b7b0da0b9efff19.jpg	ffff73a3e3f3613b
+2024-03-30	abc	./data_raw_all/4.4_17dcdf511a69ffe7708460ccf04a7b52.jpg	d07c7ae3e3f23880
+2024-03-30	abc	./data_raw_all/4.4_2153_zeiger4_2019-06-01T205012.jpg	feffc78703431b0b
+2024-03-30	abc	./data_raw_all/4.4_2155_zeiger4_2019-06-01T211012.jpg	feffc78703031b19
+2024-03-30	abc	./data_raw_all/4.4_2276_zeiger3_2020-06-15_19-06-47.jpg	ffff7fe767420000
+2024-03-30	abc	./data_raw_all/4.4_2277_zeiger4_2019-06-02T085009.jpg	fbff478703031379
+2024-03-30	abc	./data_raw_all/4.4_2282_zeiger4_2019-06-04T185009.jpg	fbffc70703031371
+2024-03-30	abc	./data_raw_all/4.4_23cdf09afb7a329da507065b4f2e0786.jpg	fcfcfe26c646e3b3
+2024-03-30	abc	./data_raw_all/4.4_56d6074aa71c252d4256c86f7d224327.jpg	ffff6f6307030303
+2024-03-30	abc	./data_raw_all/4.4_625d0036b6dd3d73113437bb0e9cc17b.jpg	8b397183c3e3f3f9
+2024-03-30	abc	./data_raw_all/4.4_7a43d7be2291c5ce871fe11e8cfc0780.jpg	fcfefee6e6323020
+2024-03-30	abc	./data_raw_all/4.4_b7479f535ae747907bdde5a3bead7c19.jpg	ffff7f2707020303
+2024-03-30	abc	./data_raw_all/4.4_pointer_20211008-080205.jpg	e381808086f0f2fa
+2024-03-30	abc	./data_raw_all/4.4_pointer_20211009-184610.jpg	e3818080a6f0f0f2
+2024-03-30	abc	./data_raw_all/4.5.jpg	9c7f6703c743f373
+2024-03-30	abc	./data_raw_all/4.5_2227_zeiger3_2019-11-19_01-37-02.jpg	ffffc787e7e7c000
+2024-03-30	abc	./data_raw_all/4.5_2281_zeiger4_2019-06-04T074009.jpg	fcfec78703431379
+2024-03-30	abc	./data_raw_all/4.5_2283_zeiger4_2019-06-06T102009.jpg	fcffc78783431373
+2024-03-30	abc	./data_raw_all/4.5_470dd83d1ebe646a2b17989ac15c97d8.jpg	d87c7ac3e3f23c80
+2024-03-30	abc	./data_raw_all/4.5_4cd3cc2f64e93bab61ba727317ddc3f4.jpg	8bb9b183c3e3f3f9
+2024-03-30	abc	./data_raw_all/4.5_563c7e7309505197b5a72302f541b319.jpg	ffffe7e3e3f3f03e
+2024-03-30	abc	./data_raw_all/4.5_5c0d55e1d2e7a6573e36b5be5baa6346.jpg	ffff7f6323030305
+2024-03-30	abc	./data_raw_all/4.5_64b9d8fa0f646c8b7007a7ef4d53d930.jpg	ffffe6e0e0e0e0e0
+2024-03-30	abc	./data_raw_all/4.5_7667a61d729712bb4f450d304dd3aa42.jpg	fffbbd3c24000000
+2024-03-30	abc	./data_raw_all/4.5_a1f76999bb3e88f22100ae65b68b70b0.jpg	fffff76303230303
+2024-03-30	abc	./data_raw_all/4.5_ana1_20220626-050213.jpg	bfffc785c162c3f7
+2024-03-30	abc	./data_raw_all/4.5_ana3_20220629-225731.jpg	ffffe383e323d314
+2024-03-30	abc	./data_raw_all/4.5_ana4_20220627-003217.jpg	ffff63a323231317
+2024-03-30	abc	./data_raw_all/4.5_b47a362895c8e909dfc929468c50deab.jpg	fcfefef0f3221110
+2024-03-30	abc	./data_raw_all/4.5_d0ad4e791ffbc7356de8dc8382ca46b0.jpg	fdfff6e3c3e0d0b0
+2024-03-30	abc	./data_raw_all/4.5_d7b47aeb326fc38eac5e4c643e71a720.jpg	ffc3c18183d7fde3
+2024-03-30	abc	./data_raw_all/4.5_f311f8309d5d3e37634bdba27005b61d.jpg	ffffe383e3e3533f
+2024-03-30	abc	./data_raw_all/4.5_f7f57eec572bf8ad1be8b5991689e205.jpg	fffbbd3d25048000
+2024-03-30	abc	./data_raw_all/4.6.jpg	c3819980c3e2f3f3
+2024-03-30	abc	./data_raw_all/4.6_0d06bf733ca5dcd40da5e2ab0bcc2457.jpg	fcf8f0c0e0e0f0f8
+2024-03-30	abc	./data_raw_all/4.6_0f1353f0ed208e7a6228b5fbaac7bf63.jpg	979f070303071717
+2024-03-30	abc	./data_raw_all/4.6_1ea28f634a44dbe1b67cce91d96b08c2.jpg	fffbf9f880c0c000
+2024-03-30	abc	./data_raw_all/4.6_2235_zeiger1_2019-06-02T084009.jpg	ffffe7e1e0c0c0b0
+2024-03-30	abc	./data_raw_all/4.6_2239edc09b2766c67a72a3e6bbf1014b.jpg	ffffe7c3c3435210
+2024-03-30	abc	./data_raw_all/4.6_2288_analog3_20200817-140118.jpg	fffff3c383e2e3d1
+2024-03-30	abc	./data_raw_all/4.6_2350_zeiger3_2019-09-15_05-50-13.jpg	ffffdea3c342d3f3
+2024-03-30	abc	./data_raw_all/4.6_2362_analog3_20200814-071728.jpg	ffffe387c322c3f7
+2024-03-30	abc	./data_raw_all/4.6_2364_analog4_20200822-113944.jpg	3fbf5703a363c3f7
+2024-03-30	abc	./data_raw_all/4.6_2405_zeiger4_2019-11-19_01-42-03.jpg	ffff43a3e3e397ff
+2024-03-30	abc	./data_raw_all/4.6_27d2266faf2bfe76dd8352883821c61c.jpg	fcbc7e26c642e7a7
+2024-03-30	abc	./data_raw_all/4.6_41e54d15aa177df1f4250ec974b464cc.jpg	fdfee2e1c0e0f2f0
+2024-03-30	abc	./data_raw_all/4.6_425617a1ba070f2b74681c1e25c321f7.jpg	f87c78c3e7f23680
+2024-03-30	abc	./data_raw_all/4.6_60885ed90b97eff521f03584105fdb48.jpg	fcfefef9d0260010
+2024-03-30	abc	./data_raw_all/4.6_810f8cd866ca6311d3d09c00edc674f1.jpg	fcfc7e26c642e5e7
+2024-03-30	abc	./data_raw_all/4.6_9bf7e49732cffd30a2bd0d1934a8f3da.jpg	bfbf670303070300
+2024-03-30	abc	./data_raw_all/4.6_analog3_20200925-194829.jpg	ffff7f2727060000
+2024-03-30	abc	./data_raw_all/4.6_cb9f459bf242e4660880d4f3863be4dc.jpg	fffff6c3c3424200
+2024-03-30	abc	./data_raw_all/4.6_d0c67f28c0153c2e1595be0f815c9423.jpg	3fff67c3c2e2f1e3
+2024-03-30	abc	./data_raw_all/4.6_dc3fa6c0e721fad57dee7aa690898c6d.jpg	fcfcfe26c642e3a7
+2024-03-30	abc	./data_raw_all/4.6_pointer_20211012-110728.jpg	e7818080e6f4f0f0
+2024-03-30	abc	./data_raw_all/4.7_089fbd23f768f780534e42304e790a9f.jpg	f9fefee161231208
+2024-03-30	abc	./data_raw_all/4.7_0ec27906015bf4018763b02762c1e6db.jpg	83bdb183e3e3f3f3
+2024-03-30	abc	./data_raw_all/4.7_19af8cba3f725dad8326b170ed6eb793.jpg	f7fee1c3e3e2e3fa
+2024-03-30	abc	./data_raw_all/4.7_2217_zeiger2_2019-11-19_04-02-03.jpg	ffffcf87c5c6e0f0
+2024-03-30	abc	./data_raw_all/4.7_2360_zeiger4_2020-02-17_17-39-35.jpg	fedf6f07474787e7
+2024-03-30	abc	./data_raw_all/4.7_2397_zeiger3_2020-06-15_17-39-24.jpg	ffff7fe7e7660000
+2024-03-30	abc	./data_raw_all/4.7_4.7.jpg	83bd3881c2e2f0f0
+2024-03-30	abc	./data_raw_all/4.7_476919bd29b532fab1a6ff56676d2634.jpg	fffffec4e0e0e0e0
+2024-03-30	abc	./data_raw_all/4.7_4b7fc425cd231cf6ce776135fec76562.jpg	ffff73a3c3e3633b
+2024-03-30	abc	./data_raw_all/4.7_592bd6a69c892cb3377a13b7e0f6a2ee.jpg	fcfcfe26c646c7a7
+2024-03-30	abc	./data_raw_all/4.7_5dbf8d5742858d8e7ff0635d8faba6a6.jpg	2f270f0703070787
+2024-03-30	abc	./data_raw_all/4.7_77b71ca670498193789cdf4d14578bc9.jpg	ffffc32323438367
+2024-03-30	abc	./data_raw_all/4.7_826dcb69b828fb130348defb4c3d2677.jpg	f87c7c63e7f63480
+2024-03-30	abc	./data_raw_all/4.7_8491d18717650492fbec094b6a351688.jpg	ff9f5f0303030704
+2024-03-30	abc	./data_raw_all/4.7_9649102debb4be13caf5a68e2b72b3a8.jpg	ffff7ba3e3e3733b
+2024-03-30	abc	./data_raw_all/4.7_a568e4b4b59ef99bea090da242605601.jpg	b79f070303078717
+2024-03-30	abc	./data_raw_all/4.7_b371c6bf71deb6d914ee3b516f82aae6.jpg	fff3c18080d7fd63
+2024-03-30	abc	./data_raw_all/4.7_e3116e9ea13ab6e5c0f976efad82acf0.jpg	fdfff7e3c3425210
+2024-03-30	abc	./data_raw_all/4.8_0280623a79c9a8b70938d7200b60bb59.jpg	ffff4323a3438307
+2024-03-30	abc	./data_raw_all/4.8_0957c5e6af69781ab67742e4238696f4.jpg	e4fc7e26c646e7e7
+2024-03-30	abc	./data_raw_all/4.8_0fca88228ea40ff3d31fff62e40c9293.jpg	ffffe6c1c2e2d0d0
+2024-03-30	abc	./data_raw_all/4.8_2393_zeiger3_2019-11-19_13-07-03.jpg	ffffc787e5c7a000
+2024-03-30	abc	./data_raw_all/4.8_2414_zeiger1_2020-06-14_08-38-09.jpg	f0f0f8e4e4e0c081
+2024-03-30	abc	./data_raw_all/4.8_2439_zeiger3_2020-06-16_19-34-46.jpg	ffff7fe767240000
+2024-03-30	abc	./data_raw_all/4.8_2440_zeiger4_2020-04-29_11-20-02.jpg	fcffe6e3e3e2d211
+2024-03-30	abc	./data_raw_all/4.8_2445_zeiger4_2019-11-19_18-32-04.jpg	ffff43a3e363a7e7
+2024-03-30	abc	./data_raw_all/4.8_401174eed158eed79554a9b1fb38b4a0.jpg	fcfefefd50260000
+2024-03-30	abc	./data_raw_all/4.8_621fc62f36dd9cffc9d887a05bab3f78.jpg	fdfefee16122130b
+2024-03-30	abc	./data_raw_all/4.8_77d9b5baab24220bfbe38c826b676839.jpg	ffff472323430327
+2024-03-30	abc	./data_raw_all/4.8_875ad9ff9e02aeb4f7b5fbb6790464e1.jpg	ffff7fa787020503
+2024-03-30	abc	./data_raw_all/4.8_902cb2b846c48fd89a7c8401c8402885.jpg	ffffc72323038307
+2024-03-30	abc	./data_raw_all/4.8_965558d9267cb37f82dd7ecc7b7061bc.jpg	c3c347878782d33d
+2024-03-30	abc	./data_raw_all/4.8_analog1_20201007-155509.jpg	f0f0f8e0e0e0e0c1
+2024-03-30	abc	./data_raw_all/4.8_d88b4579194bec32d719a5233f0bebfd.jpg	ffc3c18080f7fde3
+2024-03-30	abc	./data_raw_all/4.8_f6901bd72428ee1c4ff4361daaebebb7.jpg	c3c3478787c2d39f
+2024-03-30	abc	./data_raw_all/4.8_pointer_20211021-235035.jpg	e3818080e4f4f0f4
+2024-03-30	abc	./data_raw_all/4.9_04413e06700f7217cb39fac17f5690ad.jpg	d5f1c2c0e2e3f7ff
+2024-03-30	abc	./data_raw_all/4.9_2398_zeiger4_2019-06-02T053013.jpg	ffffc78303030b07
+2024-03-30	abc	./data_raw_all/4.9_2399_zeiger4_2019-06-02T163009.jpg	fbff470703031365
+2024-03-30	abc	./data_raw_all/4.9_2400_zeiger4_2019-06-03T115009.jpg	fefec78703431367
+2024-03-30	abc	./data_raw_all/4.9_2435_zeiger3_2019-11-19_15-17-03.jpg	ffdfc787e5c78300
+2024-03-30	abc	./data_raw_all/4.9_2449_zeiger1_2019-06-02T092009.jpg	ffffe7e3c0c0c0a0
+2024-03-30	abc	./data_raw_all/4.9_2460_zeiger2_2020-06-14_15-01-14.jpg	fdfcf8e4e0e0c080
+2024-03-30	abc	./data_raw_all/4.9_2463_zeiger3_2019-09-15_06-20-12.jpg	ffffdea3c342c7e7
+2024-03-30	abc	./data_raw_all/4.9_2471_zeiger3_2019-11-19_13-57-03.jpg	ffdfc787e5c7e080
+2024-03-30	abc	./data_raw_all/4.9_2485_zeiger4_2019-09-14_12-00-12.jpg	7bff8f83c343a7e7
+2024-03-30	abc	./data_raw_all/4.9_2536_analog3_20200814-233447 - Kopie.jpg	fffff7e3c3e2e3c5
+2024-03-30	abc	./data_raw_all/4.9_4.9.jpg	ffff6fc7c342a7a3
+2024-03-30	abc	./data_raw_all/4.9_4288a1e5398d1eca2225dc9076953586.jpg	f7ffe383c3e2e3d6
+2024-03-30	abc	./data_raw_all/4.9_4bc7f875b60d385c7c9e0a6f6f2fc036.jpg	f7ffe1c1e3e2e3f2
+2024-03-30	abc	./data_raw_all/4.9_7058ded46bd1c078d124c276b7ba1af0.jpg	379f070303070707
+2024-03-30	abc	./data_raw_all/4.9_8021f30d84e2bc3188b27aff0c63329c.jpg	819d9081e3e3f3f3
+2024-03-30	abc	./data_raw_all/4.9_8e2614b11589481b2ed51a4b8f84bc42.jpg	d5f9c0c1c2e3f7ff
+2024-03-30	abc	./data_raw_all/5.0.jpg	c3c1ddc0c0e2e7f7
+2024-03-30	abc	./data_raw_all/5.0_007a7845b86bad6c2b494b061bc64b8c.jpg	f0fc7ce3e7f63480
+2024-03-30	abc	./data_raw_all/5.0_0a71430128277405c501378b3aa25d20.jpg	f9fefee16123170f
+2024-03-30	abc	./data_raw_all/5.0_172260651db2adb3dcf95097c03cdc7d.jpg	f9fefee16123031f
+2024-03-30	abc	./data_raw_all/5.0_1b60668ee2da6182dd33770837f235b0.jpg	ffff63a3e3e36337
+2024-03-30	abc	./data_raw_all/5.0_22a6a0b4cef4c14482c73db40d33f98b.jpg	f9fe7ee16323171f
+2024-03-30	abc	./data_raw_all/5.0_2446_analog1_20200813-104010.jpg	d7fde3c2c2e3e1f7
+2024-03-30	abc	./data_raw_all/5.0_2494_analog2_20200822-105114.jpg	ffffe782c3a2e1c5
+2024-03-30	abc	./data_raw_all/5.0_2520_zeiger4_2019-06-04T141009.jpg	feffc78703031365
+2024-03-30	abc	./data_raw_all/5.0_2b7c59781e936ee675e38b746f824e73.jpg	fcfc7e26c646cdcf
+2024-03-30	abc	./data_raw_all/5.0_3af53876b589b3e74085394c9eb8c50b.jpg	ffffe3a3e3e3473f
+2024-03-30	abc	./data_raw_all/5.0_5ce74889410d91cac8b1041d4c6e1443.jpg	f5f1c0c0c2e3e7ff
+2024-03-30	abc	./data_raw_all/5.0_6441d418633a11a95c294710122713de.jpg	fcf8c0c0e0e0e0fc
+2024-03-30	abc	./data_raw_all/5.0_95478a66b9d77f2306227f03eff0ec6d.jpg	fdfff6a1c3e2c0a4
+2024-03-30	abc	./data_raw_all/5.0_ana2_20230501-145208.jpg	819dd4c1e3e3f7f7
+2024-03-30	abc	./data_raw_all/5.0_ana4_20220622-104655.jpg	ffffe3a363230397
+2024-03-30	abc	./data_raw_all/5.0_c8abfb9be43dcfe57f063b5fc5bf16ed.jpg	fefcf8e0e0e0e0a0
+2024-03-30	abc	./data_raw_all/5.0_main_ana3_20221213-124605.jpg	ffffb3210107f301
+2024-03-30	abc	./data_raw_all/5.0_pointer_20211023-031341.jpg	e3808080e4f4f0e0
+2024-03-30	abc	./data_raw_all/5.1.jpg	c3c1dcc0e0e2e5ef
+2024-03-30	abc	./data_raw_all/5.1_03a699cf47d80e3f1a4ace83d29463d0.jpg	ffffe74307070705
+2024-03-30	abc	./data_raw_all/5.1_229d7a6b0d15c90ce2a7cff7a782571a.jpg	f7ffe7c1e3e2e376
+2024-03-30	abc	./data_raw_all/5.1_2535_zeiger4_2019-11-19_01-37-02.jpg	ffff43a3e5c7a7ef
+2024-03-30	abc	./data_raw_all/5.1_2571_zeiger4_2019-06-04T100009.jpg	f9ffc78703430b65
+2024-03-30	abc	./data_raw_all/5.1_2572_zeiger4_2020-04-29_13-28-02.jpg	fefce6e3e3e2c405
+2024-03-30	abc	./data_raw_all/5.1_2573_zeiger4_2020-04-29_14-25-02.jpg	fcffe6e3e3e2c405
+2024-03-30	abc	./data_raw_all/5.1_53a2239ff7377bf453965578097a4a4a.jpg	c0deccc1e3e3e7f5
+2024-03-30	abc	./data_raw_all/5.1_61fa9c27e231ec580793626bcfda3246.jpg	ffffe72323470707
+2024-03-30	abc	./data_raw_all/5.1_7b1bedf20776c9a84682ef88155e4131.jpg	ffff472303438707
+2024-03-30	abc	./data_raw_all/5.1_8daed43c08764686af4e30cf92855a89.jpg	f7ffe5e1e3e2a376
+2024-03-30	abc	./data_raw_all/5.1_aa7a430a9853711da4ee285139fde485.jpg	feff77a3e3e36337
+2024-03-30	abc	./data_raw_all/5.1_cc3a3d2aaad0f9f9261a13f35e4dfcde.jpg	fcfefeff11000000
+2024-03-30	abc	./data_raw_all/5.1_ccbabfdfa2e6cea60e4b89228a69ebc4.jpg	ffff672323038707
+2024-03-30	abc	./data_raw_all/5.1_d223c70f3ad24ca622b36b2da63d891f.jpg	fdfefee16122070f
+2024-03-30	abc	./data_raw_all/5.2_0a029a7b72d35550e74d56984f83dbe7.jpg	fcbcfe26c646cf8f
+2024-03-30	abc	./data_raw_all/5.2_14eae547875bf34d3df41edc476fe0b9.jpg	e3c1c3838783c3bf
+2024-03-30	abc	./data_raw_all/5.2_21bc333a57ae524f2346d39c6548b756.jpg	1f1f07030707073f
+2024-03-30	abc	./data_raw_all/5.2_22896zeiger3_2020-06-16_17-03-11.jpg	ffffffe7e7440000
+2024-03-30	abc	./data_raw_all/5.2_2551_zeiger2_2019-11-19_18-47-04.jpg	ffffc787c5c6e8e0
+2024-03-30	abc	./data_raw_all/5.2_2555_zeiger2_2019-11-19_19-22-04.jpg	ffffc787c5cec8f0
+2024-03-30	abc	./data_raw_all/5.2_2568_zeiger3_2019-11-19_15-27-03.jpg	ffdfc787c5c7ca00
+2024-03-30	abc	./data_raw_all/5.2_2583_zeiger4_2019-06-02T110009.jpg	fcffc78783030b67
+2024-03-30	abc	./data_raw_all/5.2_2608_zeiger4_2019-06-02T180009.jpg	f9ffc78783430b6f
+2024-03-30	abc	./data_raw_all/5.2_28a0dd8050d4de160506e5f7415ff36e.jpg	fdfff7e1c1e2c0a4
+2024-03-30	abc	./data_raw_all/5.2_35d7eaa4cd02c4ce683c8c1e89040742.jpg	f9fcfee0c022070f
+2024-03-30	abc	./data_raw_all/5.2_40b16a812004d37dc4f775fb023baadb.jpg	f9fefee06122030f
+2024-03-30	abc	./data_raw_all/5.2_43ce70f09e1ace6be58d452044e9f095.jpg	f9fcfee061220207
+2024-03-30	abc	./data_raw_all/5.2_5c9002b177e332faa825e6e8bb10664f.jpg	e3c1e38387c283bb
+2024-03-30	abc	./data_raw_all/5.2_ana2_20220623-141701.jpg	ffffc787c746c7a4
+2024-03-30	abc	./data_raw_all/5.2_ana4_20220624-101704.jpg	ffff67a367070707
+2024-03-30	abc	./data_raw_all/5.2_analog2_20200926-081756.jpg	fffcfce4e0e08080
+2024-03-30	abc	./data_raw_all/5.2_bff5134a2b4a2eecbd389aa5d17895ca.jpg	fcfefee6e6262400
+2024-03-30	abc	./data_raw_all/5.2_d78db7bd4ec4168b856ba96823a09595.jpg	feff674383278707
+2024-03-30	abc	./data_raw_all/5.2_pointer_20211022-092259.jpg	e38080c0e0f4e0e0
+2024-03-30	abc	./data_raw_all/5.3_2538_zeiger1_2019-11-19_00-02-02.jpg	ffffcf8585c6cb2e
+2024-03-30	abc	./data_raw_all/5.3_2599_zeiger2_2019-09-14_21-50-13.jpg	fdffc7a3c342c7ef
+2024-03-30	abc	./data_raw_all/5.3_2659_zeiger4_2019-06-05T051009.jpg	fcfecf87c3430b6f
+2024-03-30	abc	./data_raw_all/5.3_2662_zeiger4_2019-11-19_06-22-03.jpg	ffff43a3e747cfef
+2024-03-30	abc	./data_raw_all/5.3_2681_zeiger3_2020-04-29_14-36-02.jpg	ffffe6c2c242c881
+2024-03-30	abc	./data_raw_all/5.3_2685_analog1_20200821-210929 - Kopie.jpg	dff5eb82c3c6e1e5
+2024-03-30	abc	./data_raw_all/5.3_74d1015d2773d882df259f01e1e3dad9.jpg	e3c1c3838782833b
+2024-03-30	abc	./data_raw_all/5.3_84c20b8e22b48cfdb97a445df75a4a50.jpg	ffc3c080e0f7fde3
+2024-03-30	abc	./data_raw_all/5.3_917aa5902144e6219195dcbc1ca4e42a.jpg	e3e1c3838783c33b
+2024-03-30	abc	./data_raw_all/5.3_ce0069f4279eb252d9ef63060fb47b9b.jpg	f7f7e583c3e26766
+2024-03-30	abc	./data_raw_all/5.3_e046159c358ff9fdc11dc68ec08f8d42.jpg	c0decee0e3e3e7e5
+2024-03-30	abc	./data_raw_all/5.3_ee29a65da706e0d81603f4a191291f8e.jpg	ffdfbcb4a4408000
+2024-03-30	abc	./data_raw_all/5.3_ee8a355f02c09af39f48a8b8d3ec7d91.jpg	ffffe6e3c2e2e4a0
+2024-03-30	abc	./data_raw_all/5.4.jpg	e3c1dcc0e0e2efef
+2024-03-30	abc	./data_raw_all/5.4_177e69f971cf04be059d41c050a59861.jpg	fdfee4c0e0e0c1e4
+2024-03-30	abc	./data_raw_all/5.4_1a5a3750b17206846cff8d80b1247786.jpg	feff67a3c3e3673f
+2024-03-30	abc	./data_raw_all/5.4_209429b75e95e367732f4f4d833feea1.jpg	fffff6e1c1e2e4c0
+2024-03-30	abc	./data_raw_all/5.4_2632_zeiger1_2019-09-14_13-30-12.jpg	ffffe7e3c3c30f8f
+2024-03-30	abc	./data_raw_all/5.4_2682_zeiger3_2020-06-14_08-56-07.jpg	ffffffe7674e0000
+2024-03-30	abc	./data_raw_all/5.4_2683_zeiger4_2019-06-05T204009.jpg	fbff470703030b6d
+2024-03-30	abc	./data_raw_all/5.4_2709_zeiger4_2019-09-14_11-40-12.jpg	fcfeef87c3c3cfef
+2024-03-30	abc	./data_raw_all/5.4_4c1d5a2bea926c9966e2182d97be68fe.jpg	fffbfd9c80c0c000
+2024-03-30	abc	./data_raw_all/5.4_5.5.jpg	9c3f67034747cf4f
+2024-03-30	abc	./data_raw_all/5.4_5658e60b82d1c70e24116a95a17bd7ee.jpg	979f470303070f07
+2024-03-30	abc	./data_raw_all/5.4_5e45fa57ff14aac6965f69665a404a31.jpg	d8fc7ce2e7ee2c80
+2024-03-30	abc	./data_raw_all/5.4_81bc9be226fc2147186eca9f2b783d24.jpg	fcf8c0e0e0c0e8fc
+2024-03-30	abc	./data_raw_all/5.4_8dd26a2247686683f763c53474712b7a.jpg	b78f070303070f87
+2024-03-30	abc	./data_raw_all/5.4_97c63208892ea72b36c2c76ae0695970.jpg	fcfefe7f17010000
+2024-03-30	abc	./data_raw_all/5.4_c316cd3214e78ea17ee55e6c752db1da.jpg	ffc3c180e0f4fd63
+2024-03-30	abc	./data_raw_all/5.4_f38238a6b1d53f7193763bd366eeff37.jpg	d5f1c0c1c6e7e7ff
+2024-03-30	abc	./data_raw_all/5.4_main_ana3_20221213-130105.jpg	ffff83010161f303
+2024-03-30	abc	./data_raw_all/5.4_main_ana3_20221213-134708.jpg	ffdfa30101e791a3
+2024-03-30	abc	./data_raw_all/5.4_pointer_20211008-102957.jpg	e38180e0e0e4e8e0
+2024-03-30	abc	./data_raw_all/5.5_1db0be8d49c5189e5eddac2f9979e6f0.jpg	ffffe2c0c0c2e4fd
+2024-03-30	abc	./data_raw_all/5.5_2696_zeiger4_2019-06-06T055009.jpg	fefecf8783430b6d
+2024-03-30	abc	./data_raw_all/5.5_2700_zeiger4_2019-11-19_09-07-03.jpg	ffff43a3c547cfff
+2024-03-30	abc	./data_raw_all/5.5_2723_zeiger3_2020-06-14_12-15-54.jpg	ffff7fe7e74e0800
+2024-03-30	abc	./data_raw_all/5.5_2740_zeiger2_2020-04-29_13-31-02.jpg	fffdf6a0e0c080c0
+2024-03-30	abc	./data_raw_all/5.5_2756_zeiger4_2020-04-29_13-25-02.jpg	fcfdf6e3e3e2cc15
+2024-03-30	abc	./data_raw_all/5.5_2f57e5d28c516450e32a34b5d57d6b5b.jpg	ffffe6c3c2c2c4c0
+2024-03-30	abc	./data_raw_all/5.5_43ab20aca8f3add37c4f2facb4096028.jpg	ffff672303470747
+2024-03-30	abc	./data_raw_all/5.5_464966c1ce318f2e47eff421aa69a752.jpg	fffff76307070f0f
+2024-03-30	abc	./data_raw_all/5.5_622e6de9cce0d6d4682e28c5bd578f59.jpg	c0cecee0e0e3e7cf
+2024-03-30	abc	./data_raw_all/5.5_ana3_20220624-071704.jpg	ffffc783c546cb0c
+2024-03-30	abc	./data_raw_all/5.5_ana4_20220629-224731.jpg	ffffe7a163230797
+2024-03-30	abc	./data_raw_all/5.5_c307f0b1a3c99ffd4c3f77b95a47a405.jpg	d87c7e62e7ee3c80
+2024-03-30	abc	./data_raw_all/5.5_f02eb417fef6b298060a03a203691fb2.jpg	ffcfc080e0e4ff63
+2024-03-30	abc	./data_raw_all/5.6_07ce6246e6206d7a65436c016c70c097.jpg	ffcb8080e0e1fde3
+2024-03-30	abc	./data_raw_all/5.6_1f48d6bd3fc40354b9253b4352c4c554.jpg	feff6763a3a7cf47
+2024-03-30	abc	./data_raw_all/5.6_2724_analog2_20200817-031512.jpg	ffffe782c386c1c5
+2024-03-30	abc	./data_raw_all/5.6_2725_analog3_20200817-050544.jpg	ffffe7e383c2c3c5
+2024-03-30	abc	./data_raw_all/5.6_2735_zeiger2_2019-09-14_13-30-12.jpg	7dffe7a3c343cfe7
+2024-03-30	abc	./data_raw_all/5.6_2736_zeiger2_2019-09-14_22-50-13.jpg	7dffcfa3c343cfcf
+2024-03-30	abc	./data_raw_all/5.6_2755_zeiger4_2019-06-06T101009.jpg	fcfecf8783030f6f
+2024-03-30	abc	./data_raw_all/5.6_2760_zeiger4_2020-04-29_13-09-02.jpg	f8fee6e3e3e2cc15
+2024-03-30	abc	./data_raw_all/5.6_2808_zeiger2_2020-04-29_12-59-02.jpg	fffde6a0e1c280c0
+2024-03-30	abc	./data_raw_all/5.6_2dc3f2f1fee610ad878915c769112cef.jpg	fbffe2c0c2c2ccf5
+2024-03-30	abc	./data_raw_all/5.6_628319f087e15ba2b0815bdf2b7b685a.jpg	fcfc7c26c646cf9f
+2024-03-30	abc	./data_raw_all/5.6_9aa1bbad768e2101b346dccff6bc9b45.jpg	ffffe7a3c3e7473f
+2024-03-30	abc	./data_raw_all/5.6_ana1_20220817-100440.jpg	ffffe78707078387
+2024-03-30	abc	./data_raw_all/5.6_d23b6669b33302d2ab3190aeb8eb0d62.jpg	c07c7e60e7ee1c80
+2024-03-30	abc	./data_raw_all/5.6_main_ana3_20221214-162622.jpg	ffcf8780c0e0f183
+2024-03-30	abc	./data_raw_all/5.6_pointer_20211011-201358.jpg	e380c0e0e0ece8f0
+2024-03-30	abc	./data_raw_all/5.7.jpg	e3e0ccc0e0e0cfff
+2024-03-30	abc	./data_raw_all/5.7_0ee040ffd2159b3f1f5e2c987c048591.jpg	f5f1c0c0c7c7c7ff
+2024-03-30	abc	./data_raw_all/5.7_2726_analog4_20200817-143024.jpg	3fbf47238347c7cf
+2024-03-30	abc	./data_raw_all/5.7_2781_analog1_20200815-182423 - Kopie.jpg	dff5eb86c3c6c5c5
+2024-03-30	abc	./data_raw_all/5.7_2796_zeiger4_2019-09-14_13-20-14.jpg	7cffcf87c3c3cfdf
+2024-03-30	abc	./data_raw_all/5.7_2798_zeiger4_2019-09-15_05-50-13.jpg	fbff2f87c343cfdf
+2024-03-30	abc	./data_raw_all/5.7_2843_zeiger4_2019-06-03T210009.jpg	feffc78703030b6d
+2024-03-30	abc	./data_raw_all/5.7_28976d4fb4b7a5aded3d73e6d76739e8.jpg	f4d0e0c0e0c0c8f0
+2024-03-30	abc	./data_raw_all/5.7_41cbbe7260501c7a937c5ab4e19a7684.jpg	ffc7c8c0e0e0fd63
+2024-03-30	abc	./data_raw_all/5.7_49d23e85c90f09e0fb0c0c6818cdfcf0.jpg	fcfcfee6e62e0820
+2024-03-30	abc	./data_raw_all/5.7_4dde79b8e9eb6336f7c98b15e622a46a.jpg	f9fefee16107070f
+2024-03-30	abc	./data_raw_all/5.7_5.6.jpg	3f3f6f87c7478f1f
+2024-03-30	abc	./data_raw_all/5.7_53202090013dc227b2dc3cf24e9a978f.jpg	f7c7c0c0e0e1fde3
+2024-03-30	abc	./data_raw_all/5.7_53bc2d481422e0906e7c91c10e92c1af.jpg	ffcf90c0e0e9fde3
+2024-03-30	abc	./data_raw_all/5.7_776fd489b0edb094b1f22369dcf52d72.jpg	ffffeee0c0c0c0e0
+2024-03-30	abc	./data_raw_all/5.7_ana4_20220624-100204.jpg	ffff67a347470f07
+2024-03-30	abc	./data_raw_all/5.7_bb102aa247cc11820064a3e2aca38264.jpg	e3fdf6e0c2c0c2fd
+2024-03-30	abc	./data_raw_all/5.7_e0c67dbf9f3ee7533e70af7ceda4689f.jpg	f9fefee367070f07
+2024-03-30	abc	./data_raw_all/5.7_e50495abc5bf227f64168bf61451db77.jpg	f87c7e60e7ee1e80
+2024-03-30	abc	./data_raw_all/5.8.jpg	ffff67c3c3428dd7
+2024-03-30	abc	./data_raw_all/5.8_0dae293b6534f128f5de692b06cae204.jpg	f7ffe783c3c6c7d6
+2024-03-30	abc	./data_raw_all/5.8_1b10131624a66a15fe78778f42a9863b.jpg	fcbcfe26c6c6cfbd
+2024-03-30	abc	./data_raw_all/5.8_272d020518fb10379ac2a2dd284a3194.jpg	d5d1c0c1c7c7c7ff
+2024-03-30	abc	./data_raw_all/5.8_2810_analog1_20200819-010922.jpg	d7fdef82c3c6c1df
+2024-03-30	abc	./data_raw_all/5.8_2818_analog3_20200818-165523.jpg	ffffe7e3c3c6c3cd
+2024-03-30	abc	./data_raw_all/5.8_2825_zeiger1_2019-09-14_19-20-12.jpg	ffffe7e3c3c38f97
+2024-03-30	abc	./data_raw_all/5.8_2850_analog3_20200813-232223.jpg	ffffe783c346c3f7
+2024-03-30	abc	./data_raw_all/5.8_2860_zeiger1_2020-04-29_11-44-02.jpg	f5fce2e0e0c0c0c0
+2024-03-30	abc	./data_raw_all/5.8_2892_zeiger4_2020-04-29_14-17-02.jpg	fefee6e3e3c2cc15
+2024-03-30	abc	./data_raw_all/5.8_2be710323fcd8cbf32b7dec8d961723f.jpg	f1f1c1818782c33f
+2024-03-30	abc	./data_raw_all/5.8_357537d3f4a19e6b30b5ebb805fbe6ff.jpg	feff77a3e3e3473f
+2024-03-30	abc	./data_raw_all/5.8_73e0dd5d5c3904afb4a8b2f68c37ff18.jpg	f9ffe2e1c0c2c4fd
+2024-03-30	abc	./data_raw_all/5.8_959c1f746433a2d4f1a5e4f4a91f4758.jpg	e0fc7e60e6ee1e80
+2024-03-30	abc	./data_raw_all/5.8_ana2_20220629-154729.jpg	ffffe783c3c7c5d4
+2024-03-30	abc	./data_raw_all/5.8_analog1_20200927-150752.jpg	f0f0f8e0e0c0c0c0
+2024-03-30	abc	./data_raw_all/5.8_d7563746c4a7014724c31a744ca00c62.jpg	ffff672303078f07
+2024-03-30	abc	./data_raw_all/5.8_f0dbafc97ed915971cc02bf7d70bfa5b.jpg	f0f0e0c181c2d33f
+2024-03-30	abc	./data_raw_all/5.8_f65d1a889893a77c4e6ea99d4f222522.jpg	f9fef66165070f0f
+2024-03-30	abc	./data_raw_all/5.8_fa6ba127a1b88c4aacb3dfffd5fc3f34.jpg	f7cf9eb6c4408000
+2024-03-30	abc	./data_raw_all/5.8_main_ana3_20221213-125605.jpg	ffcf9301c1c1f103
+2024-03-30	abc	./data_raw_all/5.9_12342fb0bad945e583bc8c8c7a21888c.jpg	e0ccc6e0e0e3cfdf
+2024-03-30	abc	./data_raw_all/5.9_1bd68aa93326f91c007d4e39a4f7bbf8.jpg	fcfefee6e64e0c00
+2024-03-30	abc	./data_raw_all/5.9_2849_zeiger1_2019-11-19_01-17-03.jpg	ffffcf8585ca8b3e
+2024-03-30	abc	./data_raw_all/5.9_2866_zeiger1_2020-06-15_03-38-04.jpg	f0f0f8f4e4c8c081
+2024-03-30	abc	./data_raw_all/5.9_2870_zeiger2_2019-09-14_23-00-13.jpg	7dffc7a3c343cfff
+2024-03-30	abc	./data_raw_all/5.9_2888_zeiger4_2019-09-14_11-00-12.jpg	7eff8f87c3438fff
+2024-03-30	abc	./data_raw_all/5.9_2965_zeiger2_2019-11-19_06-22-03.jpg	ffffcf87cdced8e0
+2024-03-30	abc	./data_raw_all/5.9_2b67820fbe352aa59309ca0dd327c672.jpg	f7ffe7c1e3e2e7ce
+2024-03-30	abc	./data_raw_all/5.9_3bd6db53d18fd79741606c713dd82db5.jpg	ffdbd9dc80c0c000
+2024-03-30	abc	./data_raw_all/5.9_5.9.jpg	e1dccec6c0c0ccfc
+2024-03-30	abc	./data_raw_all/5.9_6.0.jpg	e3e0c8e2e0c0cfff
+2024-03-30	abc	./data_raw_all/5.9_a519558ac45fd027d6c8066839202f33.jpg	f7c7cce0e0e0fd63
+2024-03-30	abc	./data_raw_all/5.9_ana4_20220625-100210.jpg	ffff67a343070f17
+2024-03-30	abc	./data_raw_all/5.9_analog3_20201023-225653.jpg	ffff7f27070a0000
+2024-03-30	abc	./data_raw_all/6.0_0b12810ef88c50fefe79109605b2e5e2.jpg	fdfff781c3c0c494
+2024-03-30	abc	./data_raw_all/6.0_1f4beac4e2b025d5f6fffc7366fac737.jpg	d5f1c4c0c6c7dfff
+2024-03-30	abc	./data_raw_all/6.0_1f9658f19a4c733532c5494732132ce5.jpg	f5d1c4c1c6c7d7ff
+2024-03-30	abc	./data_raw_all/6.0_2897_zeiger3_2019-11-19_01-12-03.jpg	ffffc787c7cf9880
+2024-03-30	abc	./data_raw_all/6.0_2926_analog2_20200818-103602.jpg	ffffe782c3c6c1d7
+2024-03-30	abc	./data_raw_all/6.0_2927_analog3_20200821-194457.jpg	fffff7e783c6c3c1
+2024-03-30	abc	./data_raw_all/6.0_2928_analog4_20200815-210026.jpg	3fbf472383478fdf
+2024-03-30	abc	./data_raw_all/6.0_2983_zeiger4_2019-06-02T073839.jpg	fcfecf8703031b7d
+2024-03-30	abc	./data_raw_all/6.0_2992_zeiger4_2019-11-19_01-27-03.jpg	ffff67a3c5cf9fff
+2024-03-30	abc	./data_raw_all/6.0_2995_zeiger4_2020-04-29_14-02-02.jpg	fefce6e3c3c2dc15
+2024-03-30	abc	./data_raw_all/6.0_3649d93fe89689d1e6e86485a9af50fd.jpg	fdffe7e1c1c0c494
+2024-03-30	abc	./data_raw_all/6.0_4c721538a45fb16dcb211a876bffa5ef.jpg	fcf0e0c1c182d33f
+2024-03-30	abc	./data_raw_all/6.0_5cd4d1d14fa286d803bfc68efdeb8807.jpg	f0f0c0808182c33f
+2024-03-30	abc	./data_raw_all/6.0_990500d6af9acde97da6c3b9324c7d9c.jpg	e0ece6e0e0c3cfdf
+2024-03-30	abc	./data_raw_all/6.0_a097549a853bd51bdac91e7fbd356373.jpg	f7fee7c1c1e2c7ce
+2024-03-30	abc	./data_raw_all/6.0_pointer_20211009-201242.jpg	e3c0e0e0e0e8f8f0
+2024-03-30	abc	./data_raw_all/6.1_0471f80dc91854e8549435a96bdf5e01.jpg	fdffe6c1c0c2cc90
+2024-03-30	abc	./data_raw_all/6.1_061dd6b290c737a1e72c41d98feecfe0.jpg	fff8e0c0c180c33f
+2024-03-30	abc	./data_raw_all/6.1_0f8cc04837a6c32fd34348152a1e1643.jpg	fffffee3c3c40201
+2024-03-30	abc	./data_raw_all/6.1_11649e59b8791e5dfb8736ab0f6750a5.jpg	d0e0e0e0e0c0f0f0
+2024-03-30	abc	./data_raw_all/6.1_3001_zeiger1_2019-11-19_01-47-03.jpg	ffffcf85858a9b7e
+2024-03-30	abc	./data_raw_all/6.1_3003_analog2_20200821-084240.jpg	ffffe786c346c1d5
+2024-03-30	abc	./data_raw_all/6.1_3004_analog3_20200819-092654.jpg	ffffe7e7c3c6c3d5
+2024-03-30	abc	./data_raw_all/6.1_3010_zeiger2_2019-11-19_01-22-03.jpg	ffffcf878d8e98f0
+2024-03-30	abc	./data_raw_all/6.1_3013_zeiger2_2020-06-14_11-50-46.jpg	fcfcf8e4e0c88080
+2024-03-30	abc	./data_raw_all/6.1_3020_zeiger3_2019-11-19_06-27-03.jpg	ffdfc787c5cf8800
+2024-03-30	abc	./data_raw_all/6.1_3091_zeiger4_2020-04-29_12-17-02.jpg	f8fee6e3c3c2dc15
+2024-03-30	abc	./data_raw_all/6.1_32acefae9d4454ead084f44b91d35e38.jpg	f7c1cee6e4e0f963
+2024-03-30	abc	./data_raw_all/6.1_3d0d1251befb160b3b205a7a01369fa2.jpg	ffcf9ef6c4488000
+2024-03-30	abc	./data_raw_all/6.1_5fa0c7d57cff21da2bd6a6c42c958a18.jpg	f7ffe7e3c1c2c75e
+2024-03-30	abc	./data_raw_all/6.1_6a6cbb6e03c3e3abb97806eab4fc5b3d.jpg	fef0e0c0c182f33f
+2024-03-30	abc	./data_raw_all/6.1_8e288076ef20955606137b8fb256e2a0.jpg	f6c7cee4e4e8f9e3
+2024-03-30	abc	./data_raw_all/6.1_961275bd37e08d1d31f7eeecb40d2ba0.jpg	f0ece6e2e0c2dfdd
+2024-03-30	abc	./data_raw_all/6.1_988598a8927b5d2f0fa25d825f32927b.jpg	ffffe7e3e3cfd43e
+2024-03-30	abc	./data_raw_all/6.1_a1500e3f3187c4cede044a4487e02b7d.jpg	e8fc7e64e6ee3c80
+2024-03-30	abc	./data_raw_all/6.1_analog1_20200925-063145.jpg	f0f0f8f0e0c8d0c0
+2024-03-30	abc	./data_raw_all/6.1_ba20efe7193adfdcdf1b841074465634.jpg	d5f1e4c1c7c7d7ff
+2024-03-30	abc	./data_raw_all/6.1_main_ana3_20221213-140819.jpg	ffc7cfc3e260f901
+2024-03-30	abc	./data_raw_all/6.1_main_ana3_20221214-222121.jpg	ffc7dfc6e4409003
+2024-03-30	abc	./data_raw_all/6.2.jpg	f1e0e0e2c0c0fdff
+2024-03-30	abc	./data_raw_all/6.2_00ad226a79819026066f9d824c7857c6.jpg	fef8f0c0c1c093bf
+2024-03-30	abc	./data_raw_all/6.2_0f70cee2a7964eef5650522e76696618.jpg	fefd7ea4c1428101
+2024-03-30	abc	./data_raw_all/6.2_23ec872b3a5c8a44f08035d2cd82eaed.jpg	fdffe7e3c3420004
+2024-03-30	abc	./data_raw_all/6.2_3037_zeiger1_2019-09-14_20-10-12.jpg	ffffe7a3c3c39fb7
+2024-03-30	abc	./data_raw_all/6.2_3040_zeiger1_2019-09-14_20-27-35.jpg	ffffc6a3c3c397bf
+2024-03-30	abc	./data_raw_all/6.2_3089_zeiger3_2020-06-14_14-25-54.jpg	ffffffe7470a0000
+2024-03-30	abc	./data_raw_all/6.2_38841983063114d33e40762939948518.jpg	f9fefee1410f0f1f
+2024-03-30	abc	./data_raw_all/6.2_545dc08796ff546a06774c2840d337d7.jpg	f9fefee1410f1e1e
+2024-03-30	abc	./data_raw_all/6.2_6.1.jpg	f3e0e0e2e0c0ddff
+2024-03-30	abc	./data_raw_all/6.2_824573cbbde443bdd467c441c2ab242d.jpg	387c7f3f1f070300
+2024-03-30	abc	./data_raw_all/6.2_949b857328039d56a9137a9eb70f5110.jpg	e0fe7ee4e6fe3c80
+2024-03-30	abc	./data_raw_all/6.2_9bf99513d1e8236b7cd6dfc224c041d1.jpg	b87c7f3f1f0f0700
+2024-03-30	abc	./data_raw_all/6.2_ana3_20220624-075704.jpg	ffffc783850e8b3c
+2024-03-30	abc	./data_raw_all/6.2_b476e34fbd2808c1decc7eb2d85d3a7b.jpg	fefeeac0c0c090a0
+2024-03-30	abc	./data_raw_all/6.2_be5706dab5cfdf0846d17e550363c1e1.jpg	2f2f1f0703070f07
+2024-03-30	abc	./data_raw_all/6.2_bf779b6e10d44450dcc09d94857f3bf8.jpg	ffff77a3c3c3473f
+2024-03-30	abc	./data_raw_all/6.2_main_ana3_20221213-130605.jpg	ffcf8f06c141f103
+2024-03-30	abc	./data_raw_all/6.2_main_ana3_20221213-140319.jpg	ffcf8fc6c441f101
+2024-03-30	abc	./data_raw_all/6.2_main_ana3_20221213-141033.jpg	ffcf8fc6c5c0f101
+2024-03-30	abc	./data_raw_all/6.3_224dc58a03f4c4cbae5bd69672c05a3b.jpg	f7cfdef6c6488000
+2024-03-30	abc	./data_raw_all/6.3_3052_zeiger2_2019-06-02T041013.jpg	fdfee7e1c000c0e0
+2024-03-30	abc	./data_raw_all/6.3_3062_zeiger2_2019-06-05T142009.jpg	fdfee7e1c10080c0
+2024-03-30	abc	./data_raw_all/6.3_3092_analog4_20200814-123000.jpg	bf7f4703c387cff7
+2024-03-30	abc	./data_raw_all/6.3_3102_zeiger1_2019-06-06T150009.jpg	ffffc7e3c08080b0
+2024-03-30	abc	./data_raw_all/6.3_3237_zeiger4_2019-06-02T185009.jpg	f9ffcf8703031b7f
+2024-03-30	abc	./data_raw_all/6.3_3243_zeiger4_2019-06-06T123009.jpg	f8ffc78783031b7d
+2024-03-30	abc	./data_raw_all/6.3_40c929fdddd4d74ddc1281813aed0384.jpg	fffee4c0c0d8a1e4
+2024-03-30	abc	./data_raw_all/6.3_727c964cca1273b3cf95106ea11fb177.jpg	d5d1e4c1c287f7ff
+2024-03-30	abc	./data_raw_all/6.3_8844ccefd3245350cbc891e50053a36a.jpg	f7ffe7e3c1c2877f
+2024-03-30	abc	./data_raw_all/6.3_8f7393000ddebebbad26196457cbb6ce.jpg	f5f1e4c1c687f7ff
+2024-03-30	abc	./data_raw_all/6.3_95084ff309c86e0653147c5e1a3f75ed.jpg	f5d1c4c1c387f7ff
+2024-03-30	abc	./data_raw_all/6.3_aa19269a0fbab1fc083afc028e30ae35.jpg	d5f1e4c0c2c7f7ff
+2024-03-30	abc	./data_raw_all/6.3_ana4_20220629-154729.jpg	ffffe7a343071f97
+2024-03-30	abc	./data_raw_all/6.3_ec88d988eb29f8d17d30af10473f8405.jpg	fff8f0e0c080813f
+2024-03-30	abc	./data_raw_all/6.4_1a508819371354464cb279a87376e931.jpg	fdfff6e1c1c284b4
+2024-03-30	abc	./data_raw_all/6.4_3110_zeiger1_2019-09-14_21-20-13.jpg	ffffe6e3c3c39fbf
+2024-03-30	abc	./data_raw_all/6.4_3172_zeiger3_2019-11-19_15-42-03.jpg	ffffc787858f8800
+2024-03-30	abc	./data_raw_all/6.4_3222_zeiger3_2019-11-19_05-02-03.jpg	ffffc787859faa00
+2024-03-30	abc	./data_raw_all/6.4_3242_zeiger4_2019-06-06T122009.jpg	f8ffcf8783031f7f
+2024-03-30	abc	./data_raw_all/6.4_3244_zeiger4_2020-04-29_10-56-43.jpg	fcfff6e3c3c2dc15
+2024-03-30	abc	./data_raw_all/6.4_3293_zeiger2_2020-04-29_11-57-02.jpg	fffdf6a0c1c090c0
+2024-03-30	abc	./data_raw_all/6.4_8dfbb1e54334c23791c2247db53ae50e.jpg	f07e7e66e6fe3c80
+2024-03-30	abc	./data_raw_all/6.4_a402cf5c3cdc400a76b1a874c24f7b04.jpg	fcf8e0e0c0d0d0fc
+2024-03-30	abc	./data_raw_all/6.4_b8472a8c37c8d9677ac98426e77a9274.jpg	f0e4e6e2c0c09ffd
+2024-03-30	abc	./data_raw_all/6.4_c0fa89df519f3e665d7778b437c7d493.jpg	ffebddcc80c0c000
+2024-03-30	abc	./data_raw_all/6.4_e6989a823abd05e4b4d5ecc856de14aa.jpg	b87c3e3f1f0f0712
+2024-03-30	abc	./data_raw_all/6.4_ede1c9c6a229920a25b9ac4e1cf30bb5.jpg	fffcf0e0c080913d
+2024-03-30	abc	./data_raw_all/6.4_pointer_20211010-122829.jpg	e3c0e0e0e0d8f8e0
+2024-03-30	abc	./data_raw_all/6.5_2a71b3cfa8eaaf451eecd36e0e5b7d2f.jpg	f7c1ccf6e6e0f963
+2024-03-30	abc	./data_raw_all/6.5_3117_zeiger1_2019-09-15_05-10-12.jpg	ffffe6a3c383bfbf
+2024-03-30	abc	./data_raw_all/6.5_3156_zeiger3_2019-11-19_02-27-03.jpg	ffffc787878fb800
+2024-03-30	abc	./data_raw_all/6.5_3159_zeiger3_2019-11-19_02-42-03.jpg	ffffc787878faa80
+2024-03-30	abc	./data_raw_all/6.5_3246_analog4_20200817-163844.jpg	3fbf472783078fff
+2024-03-30	abc	./data_raw_all/6.5_3272_zeiger1_2020-06-14_09-40-16.jpg	f0f0f8e4e4c8a0c1
+2024-03-30	abc	./data_raw_all/6.5_3337_zeiger4_2020-04-29_13-49-02.jpg	fcfcf6e3c382dc15
+2024-03-30	abc	./data_raw_all/6.5_3345_zeiger2_2020-04-29_12-05-02.jpg	fffdf6a0c08290c0
+2024-03-30	abc	./data_raw_all/6.5_3fcd2983f990c95ac6b40e583405d178.jpg	f7c1cce6e4e8f1e3
+2024-03-30	abc	./data_raw_all/6.5_3fe99d8d606d17e81cc4252cf2df29e5.jpg	fcfefee6c61e3c00
+2024-03-30	abc	./data_raw_all/6.5_6.4.jpg	f9f0e0e2c080fdff
+2024-03-30	abc	./data_raw_all/6.5_98a0eff9b1d428320a0a2b032ce734a9.jpg	fffff6c3c2c29cf0
+2024-03-30	abc	./data_raw_all/6.5_b084e9d9f9c53b6eece5694ba11b8be7.jpg	fffff783c3874f3f
+2024-03-30	abc	./data_raw_all/6.6.jpg	9f3f670387073f7f
+2024-03-30	abc	./data_raw_all/6.6_178398159633e7876984612421939c40.jpg	f9fefee1400a1d03
+2024-03-30	abc	./data_raw_all/6.6_1c59da9a571cacefc866f2c4fd9c946d.jpg	ffff670303070f27
+2024-03-30	abc	./data_raw_all/6.6_3193_zeiger1_2019-11-19_02-17-03.jpg	ffffcf85850abbfe
+2024-03-30	abc	./data_raw_all/6.6_3278_analog1_20200813-182243.jpg	97fde7c2c287d5f7
+2024-03-30	abc	./data_raw_all/6.6_3291_zeiger2_2019-09-15_05-20-12.jpg	7dffc7a3c38297ff
+2024-03-30	abc	./data_raw_all/6.6_3295_zeiger3_2019-09-14_22-50-13.jpg	ffffdea3830297ff
+2024-03-30	abc	./data_raw_all/6.6_3296_zeiger3_2020-06-16_19-30-34.jpg	ffff7fe7c71a0000
+2024-03-30	abc	./data_raw_all/6.6_32f8960168ad68dd0ce3eb6e9365fa1b.jpg	f0747c66e4fe3c80
+2024-03-30	abc	./data_raw_all/6.6_3343_zeiger2_2019-11-19_01-27-03.jpg	ffffcf87859ef8f0
+2024-03-30	abc	./data_raw_all/6.6_3353_zeiger3_2020-04-29_11-57-02.jpg	ffffe6c282029881
+2024-03-30	abc	./data_raw_all/6.6_46be518d62e8bb58e625826d7918a4d7.jpg	fffffee3c3020000
+2024-03-30	abc	./data_raw_all/6.6_5364a9fa3ebeb26c5d32aad631207f44.jpg	ffffe70303078f0f
+2024-03-30	abc	./data_raw_all/6.6_5cd3c768c09965a9e5d23d5b21ea5d3b.jpg	ffff7e27c3020507
+2024-03-30	abc	./data_raw_all/6.6_70cb80541792d6ed5a2d8d3a7be6b51b.jpg	f7fee7c3c1c287fe
+2024-03-30	abc	./data_raw_all/6.6_8592f7a6223a2a71f41c425e7dc3a2f8.jpg	3c3c3e3f1f0f0716
+2024-03-30	abc	./data_raw_all/6.6_ana3_20220626-050213.jpg	ffffc783810ecb0c
+2024-03-30	abc	./data_raw_all/6.6_bbeaf4f3ed8a5710f298fafaf7dd8441.jpg	f7ffe583c38687f6
+2024-03-30	abc	./data_raw_all/6.6_e3ca06ba37b4fcd7ec3ad303dc244532.jpg	f0e6e6e2c080bfff
+2024-03-30	abc	./data_raw_all/6.6_main_ana3_20221215-064620.jpg	ffc3cfe6c6448003
+2024-03-30	abc	./data_raw_all/6.6_pointer_20211014-210029.jpg	e3e0f0f0e0f8f8e0
+2024-03-30	abc	./data_raw_all/6.7_11894a97fdf06e9f9afdb270a4cab3b3.jpg	ffe1e8f0e4e0f963
+2024-03-30	abc	./data_raw_all/6.7_215dd11a21aaffe9aa70128b91ca8dfe.jpg	ffff73a3c3834f3f
+2024-03-30	abc	./data_raw_all/6.7_3342_zeiger1_2020-06-16_04-11-03.jpg	f0f0f8e4c4d8e081
+2024-03-30	abc	./data_raw_all/6.7_3365_zeiger1_2019-11-19_02-37-03.jpg	ffffcf85850efbbe
+2024-03-30	abc	./data_raw_all/6.7_3435_zeiger1_2019-11-19_04-42-03.jpg	ffff4f85850afb3e
+2024-03-30	abc	./data_raw_all/6.7_527cbc933b9fc8e35443efd1281f6f5b.jpg	7c3c3e3f1f1f0f06
+2024-03-30	abc	./data_raw_all/6.7_5e9374a993e70ae14d6362065fdf678c.jpg	f0f47664e4fe3c80
+2024-03-30	abc	./data_raw_all/6.7_6fd2eb6346043d9d720188b3825ec655.jpg	ffc3dee6c66c8000
+2024-03-30	abc	./data_raw_all/6.7_7de7293d87c146005f77634eb1898616.jpg	fffff6e3c282fcb0
+2024-03-30	abc	./data_raw_all/6.7_analog1_20201030-213605.jpg	f0f0f8e0c0d8e0c1
+2024-03-30	abc	./data_raw_all/6.7_analog2_20201001-044319.jpg	fffcfce4c0808080
+2024-03-30	abc	./data_raw_all/6.7_bf88fadf30fc4b06e29693747eb4f351.jpg	d5d1c4c1828ff7ff
+2024-03-30	abc	./data_raw_all/6.8_097ae32ce724dfe7fbb7df70cfee44db.jpg	f8f2e6e2c080fdff
+2024-03-30	abc	./data_raw_all/6.8_316a9b8756ee729c4a068a2a2f952715.jpg	fcf8e0c080f0e0fc
+2024-03-30	abc	./data_raw_all/6.8_3411_zeiger2_2020-06-14_15-10-18.jpg	fdfcf8e4c080e080
+2024-03-30	abc	./data_raw_all/6.8_3420_zeiger4_2019-09-15_06-00-12.jpg	fcffef878303ffff
+2024-03-30	abc	./data_raw_all/6.8_3426_analog2_20200816-075213.jpg	ffffe7868306c1d7
+2024-03-30	abc	./data_raw_all/6.8_3478_zeiger4_2019-11-19_17-37-04.jpg	ffff4783830fffff
+2024-03-30	abc	./data_raw_all/6.8_52d5cd5bbc47b0cd2095cd4086fdb2e0.jpg	ffffffc4800050e0
+2024-03-30	abc	./data_raw_all/6.8_6.7.jpg	fff0e0e0c280f9ff
+2024-03-30	abc	./data_raw_all/6.8_623f331e36885917172f759b16489f84.jpg	f0f67666e4fe3e80
+2024-03-30	abc	./data_raw_all/6.8_7188809ca3751b06bd6131dcc9f16073.jpg	fffff8e0c0809139
+2024-03-30	abc	./data_raw_all/6.8_78d774c411810a37beb97c7e23bef990.jpg	fdfff7e1c180d4b4
+2024-03-30	abc	./data_raw_all/6.8_87067dea681dcb4c39dcff58663ad62b.jpg	fdffe6c380c2fcd0
+2024-03-30	abc	./data_raw_all/6.8_f89b3b77c7d47aaa185d72ec3a36a973.jpg	fffffee0c0809019
+2024-03-30	abc	./data_raw_all/6.9_11331ff62f340bc56d9c05f006e6cbcb.jpg	d0e0e0e080f0f0f4
+2024-03-30	abc	./data_raw_all/6.9_3484_zeiger4_2020-04-29_13-12-02.jpg	fefef6e3c3c2fc15
+2024-03-30	abc	./data_raw_all/6.9_3487_analog1_20200822-132556.jpg	dffde386c382edf5
+2024-03-30	abc	./data_raw_all/6.9_47882110647686aa302377ad1dfb5bf6.jpg	f5d1e4c183cff7ff
+2024-03-30	abc	./data_raw_all/6.9_51a93f6660db926095eee0de365107f9.jpg	ffffe7e3839ff43e
+2024-03-30	abc	./data_raw_all/6.9_70520571b853a616dc78e2e72d27fda4.jpg	fefdf0e0c090f0d0
+2024-03-30	abc	./data_raw_all/6.9_9a4de6c27a3cd57e40957ffb522e6282.jpg	d5f1e4c182cff7ff
+2024-03-30	abc	./data_raw_all/6.9_ba7fada72dd111abbbcc73b11fda1dd6.jpg	e0d0e0c080c0f0ff
+2024-03-30	abc	./data_raw_all/6.9_cd9c8efecb714713a8f85338085f5b71.jpg	ffc1dec6c66c0000
+2024-03-30	abc	./data_raw_all/6.9_f666dc97a4ca1b13ec98f34980d21734.jpg	fdffe7c383024204
+2024-03-30	abc	./data_raw_all/7.0_13e54f78c3285102da0627a3ea34c3fe.jpg	f7ffe3c3c382e77f
+2024-03-30	abc	./data_raw_all/7.0_17ecc3ffc44ab69e67bd55af1b71572c.jpg	3fff66c382f2b1e7
+2024-03-30	abc	./data_raw_all/7.0_1e781872e114eb9bb865763fa19dd893.jpg	f8f0f6e08080fcff
+2024-03-30	abc	./data_raw_all/7.0_3412_zeiger3_2019-11-19_17-22-04.jpg	ffffc78787dfc300
+2024-03-30	abc	./data_raw_all/7.0_3467_zeiger3_2019-11-19_17-02-03.jpg	ffffc78787dfc800
+2024-03-30	abc	./data_raw_all/7.0_3486_analog1_20200819-115303.jpg	d7fde3c28382e9f7
+2024-03-30	abc	./data_raw_all/7.0_3488_analog4_20200813-185654.jpg	bf3f4703838fcff7
+2024-03-30	abc	./data_raw_all/7.0_3489_zeiger1_2019-06-02T181009.jpg	ffffe7838080c0b0
+2024-03-30	abc	./data_raw_all/7.0_3490_zeiger1_2019-09-15_05-49-06.jpg	ffffe7e383c3ffbf
+2024-03-30	abc	./data_raw_all/7.0_3509_zeiger2_2019-06-03T162009.jpg	fdfee7818100c0c0
+2024-03-30	abc	./data_raw_all/7.0_3594_zeiger3_2019-11-19_16-02-04.jpg	ffffc78787dfea80
+2024-03-30	abc	./data_raw_all/7.0_38502b6924f019d23177a0831ec2501f.jpg	ffbf7f2783020301
+2024-03-30	abc	./data_raw_all/7.0_4ccae617488e34d16bc5c1d32f0f1b1e.jpg	ffff7ba383837f3f
+2024-03-30	abc	./data_raw_all/7.0_4f247f78495704a7d593bcc6d7657d5e.jpg	d5d1e0c082e7f7ff
+2024-03-30	abc	./data_raw_all/7.0_5624216e3feee0263cb131f7214ac03d.jpg	ffffe6c382c0fcb0
+2024-03-30	abc	./data_raw_all/7.0_5f9bd1f078f036b39eb7f92fc7559c2e.jpg	ffbf7e2783020501
+2024-03-30	abc	./data_raw_all/7.0_67a7b7f42c5bdcc9a81bda708ec11d15.jpg	feff738383836f3f
+2024-03-30	abc	./data_raw_all/7.0_9e64b1c2e2838e0a6ae5c839a77e5b06.jpg	f8727666e6fe3c80
+2024-03-30	abc	./data_raw_all/7.0_b7c72126a573ad1b76c279b6f61c0ebe.jpg	fffffec48000f0e0
+2024-03-30	abc	./data_raw_all/7.0_bff9626694b42aafc401231f3e50e8c4.jpg	3c3e3e3e1f1f0f0e
+2024-03-30	abc	./data_raw_all/7.0_pointer_20211015-060800.jpg	e3f0f0e0c0f0f8e0
+2024-03-30	abc	./data_raw_all/7.1.jpg	fff8f0c082e0f8ff
+2024-03-30	abc	./data_raw_all/7.1_00fa09e89e4064e516ea32b54cb19eed.jpg	ffe1eecec66c0000
+2024-03-30	abc	./data_raw_all/7.1_084b7c893e036c81de1f3b0978c85063.jpg	fffff38383877f3f
+2024-03-30	abc	./data_raw_all/7.1_08ecf92764f24292cfb76b25f6b5d058.jpg	ffe3f0f0e0f0f163
+2024-03-30	abc	./data_raw_all/7.1_1378bcd4d81717a8bab49bca00afac46.jpg	ffe3cdcc8cc0c000
+2024-03-30	abc	./data_raw_all/7.1_16b75a3052ed475e60c375ad85701f1d.jpg	fbffe2c08042fcf5
+2024-03-30	abc	./data_raw_all/7.1_320bb2cebee1729c01bb32aeca8247db.jpg	f87a6644e7fc3c80
+2024-03-30	abc	./data_raw_all/7.1_3536_zeiger4_2019-06-05T140009.jpg	fbffc70703031b7d
+2024-03-30	abc	./data_raw_all/7.1_3544_zeiger4_2019-09-14_22-50-13.jpg	f9ff2f870303ffff
+2024-03-30	abc	./data_raw_all/7.1_3545_analog1_20200815-230155.jpg	dff5e3c48382edf5
+2024-03-30	abc	./data_raw_all/7.1_3558_zeiger1_2019-11-19_08-52-03.jpg	ffffcf85058afb3e
+2024-03-30	abc	./data_raw_all/7.1_3603_zeiger4_2019-06-05T205009.jpg	feffcf0703031b7d
+2024-03-30	abc	./data_raw_all/7.1_3611_zeiger4_2019-06-06T092009.jpg	fefecf8703031f7f
+2024-03-30	abc	./data_raw_all/7.1_3668_zeiger4_2020-04-29_11-33-02.jpg	fcfcf6c3c3e2dc15
+2024-03-30	abc	./data_raw_all/7.1_9330c130b63288ffc504add64a67ef97.jpg	d5d1c48183eff7ff
+2024-03-30	abc	./data_raw_all/7.1_ade16080a8a438f95d00250103389d30.jpg	f9fefee1011f1f0f
+2024-03-30	abc	./data_raw_all/7.1_ana3_20220626-000213.jpg	ffffc787030ecb1c
+2024-03-30	abc	./data_raw_all/7.1_db8cb6c41d9ddb97f73cf5431b067ebc.jpg	f8f0f6e28040fcff
+2024-03-30	abc	./data_raw_all/7.2_125c2ec5cc6ac87fcd4995cc01debff9.jpg	f9fe76a1013f1f0f
+2024-03-30	abc	./data_raw_all/7.2_3528682a210b3e8ba3ca9fd528c4795e.jpg	f5d1c08182eff7ff
+2024-03-30	abc	./data_raw_all/7.2_3548_analog2_20200814-201301.jpg	ffffe3c28280e1f7
+2024-03-30	abc	./data_raw_all/7.2_3614_analog2_20200822-032757.jpg	ffffe7828302c9d5
+2024-03-30	abc	./data_raw_all/7.2_3615_analog3_20200820-054748.jpg	fffff3c38302cbc5
+2024-03-30	abc	./data_raw_all/7.2_3655_zeiger4_2019-06-03T135009.jpg	fcffc70703031f7f
+2024-03-30	abc	./data_raw_all/7.2_47756fe78ba7e662836e9ad4a1f968a4.jpg	ffffeec383064000
+2024-03-30	abc	./data_raw_all/7.2_ana1_20220629-165729.jpg	b7dfe78302cbf5f7
+2024-03-30	abc	./data_raw_all/7.2_ana4_20220629-225231.jpg	fffff383030f1f97
+2024-03-30	abc	./data_raw_all/7.2_analog1_20200927-193846.jpg	f0f0f8e0c0f0e0c0
+2024-03-30	abc	./data_raw_all/7.2_analog2_20201011-075113.jpg	fffcfce480d08080
+2024-03-30	abc	./data_raw_all/7.2_analog3_20201013-082248.jpg	ffff7f07071e0000
+2024-03-30	abc	./data_raw_all/7.2_d35bfb6c229f4eb76ac2c4029087a086.jpg	fdfff68181c2d4b4
+2024-03-30	abc	./data_raw_all/7.3.jpg	fcfcf4c080e0fcf0
+2024-03-30	abc	./data_raw_all/7.3_3640_zeiger1_2019-11-19_15-52-04.jpg	ffffcf0505cefb3e
+2024-03-30	abc	./data_raw_all/7.3_3650_zeiger2_2020-06-16_04-11-03.jpg	fdfcf8e480d0c080
+2024-03-30	abc	./data_raw_all/7.3_3672_zeiger1_2019-09-15_06-00-12.jpg	ffffe68383c3bfbf
+2024-03-30	abc	./data_raw_all/7.3_3749_zeiger4_2019-11-19_01-22-03.jpg	ffff438303dfffff
+2024-03-30	abc	./data_raw_all/7.3_3757_zeiger1_2020-04-29_13-14-02.jpg	f5fce2c0c0e0d0c0
+2024-03-30	abc	./data_raw_all/7.3_3765_zeiger2_2020-04-29_11-34-02.jpg	fffdf68080c090c0
+2024-03-30	abc	./data_raw_all/7.3_49ccb6c82ca261f12e65881ecfa0163d.jpg	fdfff6c180c0d4d0
+2024-03-30	abc	./data_raw_all/7.3_5aa20fa0d6252ff78c7dd353d3e8609c.jpg	f7ffe7c183c2e77e
+2024-03-30	abc	./data_raw_all/7.3_628055dec50be4c7ddff42caccb99ad3.jpg	fdfae4c000f8e1e4
+2024-03-30	abc	./data_raw_all/7.3_69bfb2ef4af76d0941bfa6195b38841c.jpg	fcfefec7867e3c00
+2024-03-30	abc	./data_raw_all/7.3_6fd435709d0e70bebd1cfdbe781c9b5a.jpg	ffffe78383fffc3e
+2024-03-30	abc	./data_raw_all/7.3_a4accb1ac1e16cc3d5fa1a28ccbe35e8.jpg	fff8f2c280e0f8ff
+2024-03-30	abc	./data_raw_all/7.3_main_ana3_20221213-141633.jpg	ffe3e1e0c1e0e183
+2024-03-30	abc	./data_raw_all/7.4.jpg	fff9f08080e0f0ff
+2024-03-30	abc	./data_raw_all/7.4_0f97d973863c2591cff2f191502008a0.jpg	fcfefe86863e1820
+2024-03-30	abc	./data_raw_all/7.4_3663_zeiger4_2019-11-19_19-37-04.jpg	ffff438303ff9fff
+2024-03-30	abc	./data_raw_all/7.4_3747_zeiger3_2020-06-15_17-13-42.jpg	ffffff87077a0000
+2024-03-30	abc	./data_raw_all/7.4_3752_analog2_20200815-171449.jpg	ffffe3828282e1d7
+2024-03-30	abc	./data_raw_all/7.4_3753_analog4_20200814-085140.jpg	bf3f470303ff8ff7
+2024-03-30	abc	./data_raw_all/7.4_3768_zeiger3_2019-09-14_12-30-12.jpg	ffffee830343bfe7
+2024-03-30	abc	./data_raw_all/7.4_3769_zeiger3_2019-11-19_09-57-03.jpg	ffffc78787ff8b00
+2024-03-30	abc	./data_raw_all/7.4_3796_zeiger4_2019-09-14_19-50-12.jpg	fcfeef8703c3ffff
+2024-03-30	abc	./data_raw_all/7.4_3801_zeiger4_2019-09-14_20-27-35.jpg	fcfeff8783c3f7ff
+2024-03-30	abc	./data_raw_all/7.4_501df4dd401eb2e15f8d1999f9f39638.jpg	f9ffe28080e2f4fd
+2024-03-30	abc	./data_raw_all/7.4_53a717848d79c103b2db52624895140c.jpg	ffff7b8383c36f3f
+2024-03-30	abc	./data_raw_all/7.4_5a0285ae6262f2d9845aa0dedfc8cc44.jpg	fffffe8383425000
+2024-03-30	abc	./data_raw_all/7.4_9e38bfba32bc9489798b435ac1cccb89.jpg	1c1e1e3e1e1f1f1e
+2024-03-30	abc	./data_raw_all/7.4_d99b3d20127d27677ed8398a59b0a3eb.jpg	fdfefec786240000
+2024-03-30	abc	./data_raw_all/7.4_f5db926e12941f8bdbbcf33d5f0ec8a7.jpg	ffffe38383e75f3f
+2024-03-30	abc	./data_raw_all/7.4_f70dfee8356c0e4d273ffe49ec7cab46.jpg	fffff68181c2dc90
+2024-03-30	abc	./data_raw_all/7.4_pointer_20211007-093231.jpg	f3f0f0e0e0f0f0e0
+2024-03-30	abc	./data_raw_all/7.5.jpg	fffdf08080e0f0fa
+2024-03-30	abc	./data_raw_all/7.5_11115f06dd8dc24bfb235bc720d0ccd5.jpg	fefcf08080f0f0d0
+2024-03-30	abc	./data_raw_all/7.5_1c57893fe38016cc8752aaa3835a45c4.jpg	f8fcfc860c7c3840
+2024-03-30	abc	./data_raw_all/7.5_1f981927cb4965661b9b119fa3d4063f.jpg	fdfee2818160f4f4
+2024-03-30	abc	./data_raw_all/7.5_3761_zeiger2_2019-11-19_06-32-03.jpg	ffffc70705def8f0
+2024-03-30	abc	./data_raw_all/7.5_3817_analog4_20200817-005210.jpg	3fbf57030347dfdf
+2024-03-30	abc	./data_raw_all/7.5_3827_zeiger1_2020-06-15_14-30-25.jpg	f0f0f884c4f8c0c1
+2024-03-30	abc	./data_raw_all/7.5_3829_zeiger2_2019-06-02T084009.jpg	fdfee7818040d0c0
+2024-03-30	abc	./data_raw_all/7.5_3838_zeiger3_2019-06-01T203011.jpg	ffffc7838140d1c0
+2024-03-30	abc	./data_raw_all/7.5_3843_zeiger3_2020-04-29_12-31-02.jpg	ffffe68283429881
+2024-03-30	abc	./data_raw_all/7.5_3847_zeiger4_2019-09-14_12-20-13.jpg	fcffef0783c3ffff
+2024-03-30	abc	./data_raw_all/7.5_3848_zeiger4_2020-04-29_11-57-02.jpg	fcfdf68383e2dc15
+2024-03-30	abc	./data_raw_all/7.5_530c14a2abbd3afe7c75af50d0722dda.jpg	d0e0e080a0f0f0f0
+2024-03-30	abc	./data_raw_all/7.5_5b2843cac67c2857419b95cef90922b4.jpg	f7ffe78383c26fd6
+2024-03-30	abc	./data_raw_all/7.5_7.7.jpg	fffff08080e0f0f0
+2024-03-30	abc	./data_raw_all/7.5_adfd2533f18609916526563dbeab2586.jpg	fff3f0e0e0f1e1e3
+2024-03-30	abc	./data_raw_all/7.5_ana4_20220624-153205.jpg	ffff4303035f0f07
+2024-03-30	abc	./data_raw_all/7.6_025d7bf6140a274ce1724674c7bfc644.jpg	f8f86246e6fe3c80
+2024-03-30	abc	./data_raw_all/7.6_184b2d1f91b134cb775b317b54c1a0cf.jpg	ffbf7f2703020703
+2024-03-30	abc	./data_raw_all/7.6_2d5c5f8261497c3d1d1ea9fbee525617.jpg	fdffe70383425204
+2024-03-30	abc	./data_raw_all/7.6_3816_analog3_20200819-073929.jpg	fffff7c38382ebc5
+2024-03-30	abc	./data_raw_all/7.6_3850_analog1_20200813-220615.jpg	97fde38282e3e5f7
+2024-03-30	abc	./data_raw_all/7.6_3888_zeiger4_2020-04-29_12-09-01.jpg	f8fee683c3e2dc15
+2024-03-30	abc	./data_raw_all/7.6_3913_zeiger3_2019-11-19_06-22-03.jpg	ffffc70787ffc880
+2024-03-30	abc	./data_raw_all/7.6_73d0e536745d447e90a84af0dfbad84c.jpg	fff8f08280e0f0fd
+2024-03-30	abc	./data_raw_all/7.6_ae9917755b0dba459a1215e18e1ed865.jpg	feff778383e36f3f
+2024-03-30	abc	./data_raw_all/7.6_analog1_20201003-112841.jpg	f0f0f8c0e0f8c0c0
+2024-03-30	abc	./data_raw_all/7.6_analog1_20201027-131423.jpg	f0f8f880e0f8e0c1
+2024-03-30	abc	./data_raw_all/7.6_b1f47385966f894c4dcac5cbf6330bad.jpg	ffff7e0703020507
+2024-03-30	abc	./data_raw_all/7.6_bd10ce8e4af09e4eb73a70f16dc4dd03.jpg	ffffe68380e2dcb0
+2024-03-30	abc	./data_raw_all/7.6_bf9b30d145967c3963108211787eb88a.jpg	ffe3eccec64e8000
+2024-03-30	abc	./data_raw_all/7.7_0c2412cdef4dd3c853ad612124c4248a.jpg	ffffee0383424801
+2024-03-30	abc	./data_raw_all/7.7_1093bb9f1da224c1b91492bcb00b2064.jpg	ffff7f0707020d03
+2024-03-30	abc	./data_raw_all/7.7_18ee1ae31177b08c70c8e3f63eef6d32.jpg	d5d1c081c2fff7ff
+2024-03-30	abc	./data_raw_all/7.7_20ffb634c71bab8fc9be118607e8147f.jpg	fff3eccec65e0000
+2024-03-30	abc	./data_raw_all/7.7_244d076791ca3e64b8d3322b3724fc35.jpg	f9fe7e01013f1f1f
+2024-03-30	abc	./data_raw_all/7.7_292cf2946a9f1ded9bc2f502e03de33e.jpg	0c1e1f3e1e3e1e1e
+2024-03-30	abc	./data_raw_all/7.7_3851_analog4_20200821-235348.jpg	3fbf47038367dfef
+2024-03-30	abc	./data_raw_all/7.7_3891_zeiger4_2020-04-29_13-55-01.jpg	fefce683c3e2dc15
+2024-03-30	abc	./data_raw_all/7.7_3899_zeiger3_2019-06-02T083009.jpg	ffffc70181c080c0
+2024-03-30	abc	./data_raw_all/7.7_3945_zeiger4_2019-06-02T094010.jpg	f9ff4f0703431f7f
+2024-03-30	abc	./data_raw_all/7.7_408d2a2a55ec173308dab2999b620d90.jpg	f7ffe58383e2efd6
+2024-03-30	abc	./data_raw_all/7.7_6490c173143ecaa6ebdeecd19023bb06.jpg	ffff4703034f0f27
+2024-03-30	abc	./data_raw_all/7.7_74de1aa4b242c7634af4cebf40859b7b.jpg	ffff638383e34f3f
+2024-03-30	abc	./data_raw_all/7.7_809f6c9e734960c76f9ad42472780197.jpg	ffff470303178f27
+2024-03-30	abc	./data_raw_all/7.7_ana1_20220623-143201.jpg	3fffc7058544cbff
+2024-03-30	abc	./data_raw_all/7.7_dea25d2fe06d2ee843a1993d1d53c380.jpg	fdffc683c0e2dcd0
+2024-03-30	abc	./data_raw_all/7.8_0c7d8f49a0e4855cbb35d453343abbce.jpg	ffff4f0307030f2f
+2024-03-30	abc	./data_raw_all/7.8_1b2e815c2dfd4dc2b1bee368c9ee3db5.jpg	bfdf7e8703420501
+2024-03-30	abc	./data_raw_all/7.8_20244588b67d3e8c4207203315e7dc95.jpg	ffffffe480009039
+2024-03-30	abc	./data_raw_all/7.8_210cd3384345c29c993bdb624c9eafe2.jpg	ffff4f0303478f2f
+2024-03-30	abc	./data_raw_all/7.8_2be90834c34bcd31e8e8d4729b1cba54.jpg	ffffe70303271f0d
+2024-03-30	abc	./data_raw_all/7.8_34175a9a8e1b6169ad03ab9bc69096fe.jpg	ffff4f0303438f47
+2024-03-30	abc	./data_raw_all/7.8_3928_zeiger2_2019-11-19_07-12-03.jpg	ffff070785fef8f0
+2024-03-30	abc	./data_raw_all/7.8_3950_zeiger4_2019-11-19_13-07-03.jpg	ffff4303c37b9fff
+2024-03-30	abc	./data_raw_all/7.8_3996_zeiger3_2019-11-19_17-37-04.jpg	ffff0787c5ffc800
+2024-03-30	abc	./data_raw_all/7.8_3a0a680f92b105771bfd229cf1e399e3.jpg	ffff4f0307078f07
+2024-03-30	abc	./data_raw_all/7.8_45413b99c984d009bebe98383bd1793f.jpg	ffffe783c3e34f3f
+2024-03-30	abc	./data_raw_all/7.8_7af3a2c640deb9d4fc1fcb824790869e.jpg	fbffc280c0e2fcf5
+2024-03-30	abc	./data_raw_all/7.8_934fc2f5ccf64a2442ccef6b2fa04603.jpg	ffff4f030303cf27
+2024-03-30	abc	./data_raw_all/7.8_ad7d922551c4ae2a908365edc5ca4969.jpg	ffff4f0303070f0f
+2024-03-30	abc	./data_raw_all/7.8_ana4_20220623-100200.jpg	ffffe383033f0f97
+2024-03-30	abc	./data_raw_all/7.8_ana4_20220817-100440.jpg	bccf0f07874193fd
+2024-03-30	abc	./data_raw_all/7.8_d27d41844606d52517423f1f0d5a5ad7.jpg	ffffce808060f0e0
+2024-03-30	abc	./data_raw_all/7.8_e2365055e0fc006ccd8061d3cca1197d.jpg	ffff470303430f07
+2024-03-30	abc	./data_raw_all/7.8_pointer_20211022-074259.jpg	fbf8f8e0e0f0f0e0
+2024-03-30	abc	./data_raw_all/7.9_1099905f711ef5fdc34e0f5e098fac9e.jpg	f7ffe581c3e2a7fe
+2024-03-30	abc	./data_raw_all/7.9_23a66f3611897efae00e5f8ece2fcb12.jpg	ffff4703070f0f07
+2024-03-30	abc	./data_raw_all/7.9_3921_analog4_20200814-145840.jpg	bf7f470383ffcff7
+2024-03-30	abc	./data_raw_all/7.9_3991_zeiger2_2020-06-14_16-50-43.jpg	fdfcf884c0f0c080
+2024-03-30	abc	./data_raw_all/7.9_4000_zeiger3_2020-06-15_08-55-47.jpg	ffff7f87e75e0000
+2024-03-30	abc	./data_raw_all/7.9_4003_zeiger4_2019-06-05T121009.jpg	fcfe4f0783431f7f
+2024-03-30	abc	./data_raw_all/7.9_4022_zeiger2_2019-06-02T085009.jpg	fdfec781c140d0c0
+2024-03-30	abc	./data_raw_all/7.9_4fc59d4990b9ab81712f18c24f52f6e9.jpg	fff3f1e0e0e0e163
+2024-03-30	abc	./data_raw_all/7.9_7.8.jpg	9f3f47030747bf7f
+2024-03-30	abc	./data_raw_all/7.9_7ea202456c12d3726ac4d2bfc26c4f49.jpg	d5f1c080c2f7f7ff
+2024-03-30	abc	./data_raw_all/7.9_8bb3df7709daaee885e6f47535fd425a.jpg	fff9f082c0e0f0f8
+2024-03-30	abc	./data_raw_all/7.9_ana4_20220817-100931.jpg	bfcf0f878741929d
+2024-03-30	abc	./data_raw_all/7.9_c2dda5aed2ce7d7a8ff6a073771b62ba.jpg	ffe7c18c8cc8c000
+2024-03-30	abc	./data_raw_all/8.0.jpg	fffff880e2e0f0f0
+2024-03-30	abc	./data_raw_all/8.0_10379cd7623f772faeea85bf23137b45.jpg	fcfc6046e7fe3c80
+2024-03-30	abc	./data_raw_all/8.0_25ac250d74b862ec2cc164e4b099f257.jpg	fdffc681c1e2d0b4
+2024-03-30	abc	./data_raw_all/8.0_3947_zeiger4_2019-11-19_07-27-03.jpg	ffff0383c7ffdfff
+2024-03-30	abc	./data_raw_all/8.0_4013_analog3_20200813-135936.jpg	ffffc383c322c9f7
+2024-03-30	abc	./data_raw_all/8.0_4014_analog3_20200813-170718.jpg	ffffc7838322cbf7
+2024-03-30	abc	./data_raw_all/8.0_4015_analog3_20200822-112020.jpg	ffffff0383c6dbc5
+2024-03-30	abc	./data_raw_all/8.0_4017_zeiger1_2019-09-15_06-10-12.jpg	ffffc783c3c3ff3f
+2024-03-30	abc	./data_raw_all/8.0_4020_zeiger1_2020-06-15_04-59-11.jpg	f0f0f8c4e4f8c081
+2024-03-30	abc	./data_raw_all/8.0_4034_zeiger2_2020-04-29_14-05-02.jpg	fffdd680c0e090c0
+2024-03-30	abc	./data_raw_all/8.0_4043_zeiger3_2020-04-29_13-27-02.jpg	ffffc682c2429881
+2024-03-30	abc	./data_raw_all/8.0_4044_zeiger3_2020-06-16_16-27-00.jpg	ffff7f8767180000
+2024-03-30	abc	./data_raw_all/8.0_4048_zeiger4_2019-06-06T105009.jpg	fefe0f0703431b7d
+2024-03-30	abc	./data_raw_all/8.0_4050_zeiger4_2019-06-06T150009.jpg	feff070703031b7d
+2024-03-30	abc	./data_raw_all/8.0_4051_zeiger4_2019-11-19_07-42-03.jpg	ffff0383c77b9fff
+2024-03-30	abc	./data_raw_all/8.0_4055_zeiger4_2020-04-29_14-00-02.jpg	fcffc683c3e2dc15
+2024-03-30	abc	./data_raw_all/8.0_6450ad5f5e78a53fee3907144ea1a22f.jpg	95f18081c2f7f7ff
+2024-03-30	abc	./data_raw_all/8.0_769df79ab79833aa91ca26fdd54e2490.jpg	0c0e0f1f3f3e3e3e
+2024-03-30	abc	./data_raw_all/8.0_7cb2e8df6801cdf8270e4e66d8aa60ff.jpg	fcfebe87e63e3c00
+2024-03-30	abc	./data_raw_all/8.0_91025bf02aac8cc68b861a3f9ef98cb6.jpg	ffffffc080809011
+2024-03-30	abc	./data_raw_all/8.0_9d5861cabcc8e089881a3417b70f6f62.jpg	f7f7e783c3e2efd6
+2024-03-30	abc	./data_raw_all/8.0_ana4_20220629-183230.jpg	ffff0383433f0f97
+2024-03-30	abc	./data_raw_all/8.0_e140c80812dd6399fe9cc4931c247e88.jpg	ffffc783c3f35f3f
+2024-03-30	abc	./data_raw_all/8.0_fcf8e00e910284c952b71703d32f2ac9.jpg	ffff7783c3f36f3f
+2024-03-30	abc	./data_raw_all/8.0_main_ana3_20221213-142036.jpg	fff3f1c0c1c08183
+2024-03-30	abc	./data_raw_all/8.1_0761a0280deebaeef0927f5d70b9cf92.jpg	fcfedec6e63e3c20
+2024-03-30	abc	./data_raw_all/8.1_09398153e0696e9d542daa824785f90d.jpg	f7ff8783c3e66fd6
+2024-03-30	abc	./data_raw_all/8.1_4001_zeiger4_2019-06-02T105009.jpg	f9ff0f0703031b7d
+2024-03-30	abc	./data_raw_all/8.1_4078_zeiger2_2019-09-14_13-50-13.jpg	7dffc783c343dff7
+2024-03-30	abc	./data_raw_all/8.1_4157_zeiger3_2019-11-19_00-02-02.jpg	ffdf0787e5ffc880
+2024-03-30	abc	./data_raw_all/8.1_49f580006d753735049e4e98c6c4efa8.jpg	f7fee781c3e2e77e
+2024-03-30	abc	./data_raw_all/8.1_5f96cd893b4ac27838f583d458372246.jpg	f9fe4e81613a1f1f
+2024-03-30	abc	./data_raw_all/8.1_8.1.jpg	9f7f07038747bf7f
+2024-03-30	abc	./data_raw_all/8.1_831681272346101c1cf606c92f7c0378.jpg	3fff0683e2f2d1e7
+2024-03-30	abc	./data_raw_all/8.1_90359ad05bf77b062e6ed89506645fcb.jpg	f7f7e781c3e2a77e
+2024-03-30	abc	./data_raw_all/8.1_9804055b6b52aeb1fc0b335b14a472c6.jpg	fffdc080c0e0f0f8
+2024-03-30	abc	./data_raw_all/8.1_ana3_20220629-165729.jpg	ffff8383c23fc514
+2024-03-30	abc	./data_raw_all/8.1_analog3_20201024-074802.jpg	ffff3f07271a0000
+2024-03-30	abc	./data_raw_all/8.1_e8cd5827f6d9cbb09b7004d294afae73.jpg	fffbf0e4e0e0c1e3
+2024-03-30	abc	./data_raw_all/8.2_039f7122415415002187c80e6736f869.jpg	fdff0783c3425204
+2024-03-30	abc	./data_raw_all/8.2_10a02c2f2756727650cf5f981e691edb.jpg	fdfec281c1e2fcf4
+2024-03-30	abc	./data_raw_all/8.2_22e6c1f88280864dfa3149810726848e.jpg	f9fe4e01613f1f0f
+2024-03-30	abc	./data_raw_all/8.2_2560e7cf0bdfa2a1943f729b6279a4af.jpg	ffff070347271f0d
+2024-03-30	abc	./data_raw_all/8.2_4042_zeiger3_2019-11-19_07-22-03.jpg	ffff0787e5ffcb00
+2024-03-30	abc	./data_raw_all/8.2_4057_analog1_20200816-021646.jpg	d7f5c384c3e6e9f5
+2024-03-30	abc	./data_raw_all/8.2_4062_analog2_20200814-110306.jpg	ffffc782c2a2c1d7
+2024-03-30	abc	./data_raw_all/8.2_4063_analog2_20200821-111522.jpg	ffffc782c326c9d5
+2024-03-30	abc	./data_raw_all/8.2_4101_zeiger4_2020-04-29_11-59-02.jpg	fcfc8683e3e2dc15
+2024-03-30	abc	./data_raw_all/8.2_4107_analog3_20200817-150421.jpg	ffffdf8383c2cbc5
+2024-03-30	abc	./data_raw_all/8.2_4110_zeiger1_2019-09-15_06-20-12.jpg	ffffc683e3c3ffbf
+2024-03-30	abc	./data_raw_all/8.2_4122_zeiger2_2020-06-14_08-33-40.jpg	fcfcf880e0f0c080
+2024-03-30	abc	./data_raw_all/8.2_7c1d06242eecac01affee586f8e06221.jpg	f7f58583c2e7677d
+2024-03-30	abc	./data_raw_all/8.2_8.2.jpg	ffffffc0c0e0f0f0
+2024-03-30	abc	./data_raw_all/8.2_b9f570affb75c348cc6f56d32f16dbf9.jpg	ffff87c3e3fffc3e
+2024-03-30	abc	./data_raw_all/8.3_02bc56143da209438f5adde00f2ce3c9.jpg	fefcd0c0e0f0f0d0
+2024-03-30	abc	./data_raw_all/8.3_09e4d93c6a817c412326f6a16117de28.jpg	bfbf070303070504
+2024-03-30	abc	./data_raw_all/8.3_10cc970f6ecc3baaac000b2de708ab81.jpg	f7f785c3e2a76775
+2024-03-30	abc	./data_raw_all/8.3_126a13e5717d40dfb13d9f0566020786.jpg	f9fc4e01612f1f1f
+2024-03-30	abc	./data_raw_all/8.3_289488226b7b7887939af83f3f13443f.jpg	d5d184c1c6e7f7ff
+2024-03-30	abc	./data_raw_all/8.3_4109_analog4_20200813-043852.jpg	bf7f078363dfcff7
+2024-03-30	abc	./data_raw_all/8.3_4119_zeiger2_2019-11-19_08-17-03.jpg	ffff0f87c5fef8f0
+2024-03-30	abc	./data_raw_all/8.3_4132_zeiger3_2020-06-14_16-50-43.jpg	ffff1f87e75a0000
+2024-03-30	abc	./data_raw_all/8.3_4144_analog3_20200814-005417.jpg	ffff8783c326cbf7
+2024-03-30	abc	./data_raw_all/8.3_4161_analog4_20200818-050148.jpg	3fff07038377cfff
+2024-03-30	abc	./data_raw_all/8.3_41d7410a0055bba4a336f583d8865eb7.jpg	04060f1f7f3f3e7c
+2024-03-30	abc	./data_raw_all/8.3_66ac120551a980a14ca85f0fb19de329.jpg	f7f785c3e2e7777d
+2024-03-30	abc	./data_raw_all/8.3_76ecb2694d09919237d8495271868ad1.jpg	ffff8683c2c2fcd0
+2024-03-30	abc	./data_raw_all/8.3_8.3.jpg	ffff9e80c0e4e0e0
+2024-03-30	abc	./data_raw_all/8.3_bdf2957e2842db4ec2c32ba333a787e5.jpg	d5d18481c2f7f7ff
+2024-03-30	abc	./data_raw_all/8.3_c000b42817bd4eef61edd175fcef305a.jpg	ffff8e80c0e0f0e0
+2024-03-30	abc	./data_raw_all/8.3_cc4cc79801bbbac820b0b195cf066603.jpg	ffff5f0707020f07
+2024-03-30	abc	./data_raw_all/8.3_ccd9d4fc14b62ae13bbf63888d318366.jpg	fdff86c1c0e0d4d0
+2024-03-30	abc	./data_raw_all/8.3_dc2b987ee05cda3c841c1976a9e6e004.jpg	fff3f0c6c65e0c00
+2024-03-30	abc	./data_raw_all/8.3_eb313b68b45ae4c856aa7decd3d972ca.jpg	ffff070303570f2f
+2024-03-30	abc	./data_raw_all/8.4_15c0263a48bb19f58ce3b7b3c0dd3c65.jpg	ffff1f0787020707
+2024-03-30	abc	./data_raw_all/8.4_26dccb2c146e22c83c499f23e4d91154.jpg	f9fe8e81613f1f1f
+2024-03-30	abc	./data_raw_all/8.4_4133_zeiger4_2019-06-04T121009.jpg	fcff878703431f7d
+2024-03-30	abc	./data_raw_all/8.4_4141_zeiger4_2020-04-29_13-15-02.jpg	fcfe86c3e3e2dc11
+2024-03-30	abc	./data_raw_all/8.4_4170_zeiger2_2020-06-15_19-06-47.jpg	fdfcd8c4e0d0c080
+2024-03-30	abc	./data_raw_all/8.4_4212_analog4_20200813-111418.jpg	bf3f0703a3d7cff7
+2024-03-30	abc	./data_raw_all/8.4_4584982285e245f5b4631803741da746.jpg	fcfc40c0effe3e80
+2024-03-30	abc	./data_raw_all/8.4_53b64949db739b0efc878875cca0fabf.jpg	fffbf9e4e4e0c163
+2024-03-30	abc	./data_raw_all/8.4_79f462a7c4f39585e81d31c034b53fdc.jpg	feff0703a3a79f07
+2024-03-30	abc	./data_raw_all/8.4_a2614b241520fb496aa8c04f7e52409e.jpg	b71f070303071f97
+2024-03-30	abc	./data_raw_all/8.4_a3c2cbab4c8e8f001410cb13d4e438e9.jpg	3fff86c3e2f2b9e7
+2024-03-30	abc	./data_raw_all/8.4_ana4_20220629-150229.jpg	ffff8701633f0f97
+2024-03-30	abc	./data_raw_all/8.4_analog2_20200927-150752.jpg	fffcdcc0e0d08080
+2024-03-30	abc	./data_raw_all/8.4_d49c8cceb0ad8435ece362a2c938d076.jpg	ffff8080e0e0f0f0
+2024-03-30	abc	./data_raw_all/8.4_pointer_20211009-124701.jpg	fffcf8e0e0e0c0c0
+2024-03-30	abc	./data_raw_all/8.5_04d8b22655abc8ba503a8ef5bebd48d4.jpg	ffff86c1e1e2dcd0
+2024-03-30	abc	./data_raw_all/8.5_19ff6680c7934b07ba3230441521a6d3.jpg	fdfec2c1e0e0f4f4
+2024-03-30	abc	./data_raw_all/8.5_3b3abd4281ab6190f8d3d8e8bcdf7064.jpg	fcfe4063effe3c80
+2024-03-30	abc	./data_raw_all/8.5_4205_zeiger3_2020-06-16_04-01-36.jpg	ffff9fc7675a0000
+2024-03-30	abc	./data_raw_all/8.5_4207_zeiger4_2019-09-14_21-10-12.jpg	fbff8f87c343ffff
+2024-03-30	abc	./data_raw_all/8.5_4211_analog1_20200816-075704.jpg	97f58380c3e6e9f7
+2024-03-30	abc	./data_raw_all/8.5_4241_zeiger3_2019-11-19_02-17-03.jpg	ff9f8787e5dfc800
+2024-03-30	abc	./data_raw_all/8.5_4b9567d3cff57364311ddb2a96e62c77.jpg	f7ffc7c1e3f2e77e
+2024-03-30	abc	./data_raw_all/8.5_689bdb99de46477b76a2410771ca3430.jpg	ffff8e82c2c0d8bc
+2024-03-30	abc	./data_raw_all/8.5_6f0b0f3e70c81d8197fc78060a0c2b90.jpg	ffff8783e3f74f3f
+2024-03-30	abc	./data_raw_all/8.5_8.4.jpg	ffffcfc0e0e0e0f0
+2024-03-30	abc	./data_raw_all/8.5_a52a45ad003360421626c5a8e70bf1c8.jpg	ffffdf8780809010
+2024-03-30	abc	./data_raw_all/8.6_02298a510a9907545e0c8410f57d113d.jpg	fbff82c0e0e2f4fd
+2024-03-30	abc	./data_raw_all/8.6_4026a87ac1a307e486293930a5e5b0ee.jpg	fdfe84c0e0f0e1e4
+2024-03-30	abc	./data_raw_all/8.6_4206_zeiger4_2019-06-05T044009.jpg	fcff8f8783431f7f
+2024-03-30	abc	./data_raw_all/8.6_4278_zeiger4_2019-11-19_16-57-04.jpg	ff9f8783e7f7dfff
+2024-03-30	abc	./data_raw_all/8.6_4282_analog1_20200814-004435.jpg	97ddc7c2c2e5e5f7
+2024-03-30	abc	./data_raw_all/8.6_4285_zeiger2_2019-06-01T202014.jpg	fdfe8781c040f0e0
+2024-03-30	abc	./data_raw_all/8.6_4e2d76888588b009e553d3ce4b6674eb.jpg	d0d0c0e0e0e0f8f5
+2024-03-30	abc	./data_raw_all/8.6_62f0de913d7a78286cc519fa81c96120.jpg	ff9f070323070f27
+2024-03-30	abc	./data_raw_all/8.7_0c181d56dc4d0e6f525876397327d616.jpg	f0d0c0c0e0e0f8f8
+2024-03-30	abc	./data_raw_all/8.7_1039c33b317460fb7fe86729700c9c6e.jpg	0002073f7f3f7efc
+2024-03-30	abc	./data_raw_all/8.7_34424a02db83e079d6d5926fa273b0ca.jpg	ff9f070303478f27
+2024-03-30	abc	./data_raw_all/8.7_3c3ef33ef72adc6d4ac03bb1294045ca.jpg	ff9f874307071f0d
+2024-03-30	abc	./data_raw_all/8.7_4242_zeiger4_2019-06-02T102009.jpg	fbbf8f0703031b7f
+2024-03-30	abc	./data_raw_all/8.7_4243_zeiger4_2019-06-02T191009.jpg	ffbf870703031b7d
+2024-03-30	abc	./data_raw_all/8.7_4305_zeiger2_2019-11-19_08-47-03.jpg	ff9f8f87c5def8f0
+2024-03-30	abc	./data_raw_all/8.7_4320_zeiger4_2020-04-29_12-01-02.jpg	fedec6c3e3e2dc15
+2024-03-30	abc	./data_raw_all/8.7_4339_analog2_20200813-020218.jpg	ffdfc7c2c2a4c1f7
+2024-03-30	abc	./data_raw_all/8.7_4daac85ea378d1519a38d4318ff960b9.jpg	fddfc7c3c3435204
+2024-03-30	abc	./data_raw_all/8.7_54e9e913dbc695db4d0aed7b96adc7a0.jpg	970f070303071f17
+2024-03-30	abc	./data_raw_all/8.7_68b41b5ea816ec3f01bc7dca59ef6886.jpg	ffff8683c3e2d4b4
+2024-03-30	abc	./data_raw_all/8.7_93daab00a26abd732f333767a2afac86.jpg	f7d7c5c3c3e6e7d6
+2024-03-30	abc	./data_raw_all/8.7_959bc24ef7fc7d090969b47b2f9db02a.jpg	ffff8e83c3424000
+2024-03-30	abc	./data_raw_all/8.7_9ad4fd9a15551e65c0c563d12c881d6c.jpg	ffdfc783e3f76f3f
+2024-03-30	abc	./data_raw_all/8.7_aae3ef2d654d751c015e887d5e0973a9.jpg	ffbf870323270b2f
+2024-03-30	abc	./data_raw_all/8.7_af9434b2952bd42b76bd9dc6402fb907.jpg	ffbf874347271f0d
+2024-03-30	abc	./data_raw_all/8.7_ana1_20220623-210202.jpg	3f978f85c544c3ff
+2024-03-30	abc	./data_raw_all/8.8_010511481f4e7035718c29617a32726f.jpg	fffbf8e4e69e0800
+2024-03-30	abc	./data_raw_all/8.8_1b76ce04eb8a1e93d95710889ca5ed6c.jpg	fedf4783c3f36f3f
+2024-03-30	abc	./data_raw_all/8.8_38d14a24de94cf83b178f6c1c0344bfc.jpg	ffffff8780809091
+2024-03-30	abc	./data_raw_all/8.8_39154c1662583209606ac2d9c20234a2.jpg	d5c1c0c0c2e7f7ff
+2024-03-30	abc	./data_raw_all/8.8_4294_zeiger4_2019-11-19_06-37-03.jpg	ff8f8783e77f9fff
+2024-03-30	abc	./data_raw_all/8.8_4333_zeiger4_2019-06-01T201013.jpg	fcff878703431f1f
+2024-03-30	abc	./data_raw_all/8.8_4342_analog3_20200815-063250.jpg	ffffc3c7c3e6c3d5
+2024-03-30	abc	./data_raw_all/8.8_4def02eb4bc6e58c4d0c7481a93f68b5.jpg	a090c0c0e0f0f9fa
+2024-03-30	abc	./data_raw_all/8.8_5a29699106f62f53d75f44e07bb591a1.jpg	fddac4c0e0f8e1e4
+2024-03-30	abc	./data_raw_all/8.8_5c01f502eae5b8ebc64b8208fcaef011.jpg	f98e4661613f1f1f
+2024-03-30	abc	./data_raw_all/8.8_6192db55ccc15bc498ec61f105d7ca4d.jpg	378f070303071f17
+2024-03-30	abc	./data_raw_all/8.8_6bc93d79688ceda7a51fe041de3880ff.jpg	ffffc4c0e0e0e0f0
+2024-03-30	abc	./data_raw_all/8.8_6c1d26a5619fe6399b9abc84c24c1420.jpg	ffbf4f0303070f05
+2024-03-30	abc	./data_raw_all/8.8_77b23a1066872d95e9bda164e5ab4064.jpg	f5d1c4c1e2e7f7ff
+2024-03-30	abc	./data_raw_all/8.8_78290a86802d3512e021ead22f1a1aee.jpg	a090c0c0e0f0f1f6
+2024-03-30	abc	./data_raw_all/8.8_7e0c810199cd43bfc6891e87144c4489.jpg	fcde6060effe3c80
+2024-03-30	abc	./data_raw_all/8.8_8.9.jpg	bd1f07034747ff7f
+2024-03-30	abc	./data_raw_all/8.8_a62bc0d9cf622e85afac248d7934504d.jpg	ff9fc743070f0f0f
+2024-03-30	abc	./data_raw_all/8.8_ana4_20220622-105655.jpg	ffdf478363370f97
+2024-03-30	abc	./data_raw_all/8.8_c8f48320341efd9873b8a7e738c779b2.jpg	ffff1f8783420503
+2024-03-30	abc	./data_raw_all/8.8_e5a4e88140577fb9a7fd8080dfdc0c0c.jpg	e090c0c0e0f0f0fa
+2024-03-30	abc	./data_raw_all/8.9_28349078bcc488cfaa4fc88340154a3d.jpg	ffff0f8783420d07
+2024-03-30	abc	./data_raw_all/8.9_3ea7168e61dd0fd6d98c838c8eacbb12.jpg	ffdfcec4e0e0f0e0
+2024-03-30	abc	./data_raw_all/8.9_4309_zeiger3_2019-11-19_07-27-03.jpg	ff8f8787e5ffcb00
+2024-03-30	abc	./data_raw_all/8.9_4343_analog3_20200819-011905.jpg	ffffc3c783a2cbd5
+2024-03-30	abc	./data_raw_all/8.9_4405_zeiger1_2020-06-15_16-31-01.jpg	f0f0c8e4e4d8c081
+2024-03-30	abc	./data_raw_all/8.9_4416_zeiger3_2019-09-14_11-20-12.jpg	ffdf4e83c343bfe7
+2024-03-30	abc	./data_raw_all/8.9_4425_zeiger4_2019-06-04T174009.jpg	fbdf070703031b7d
+2024-03-30	abc	./data_raw_all/8.9_4427_zeiger4_2019-09-14_11-30-12.jpg	7edf8f87c343bfff
+2024-03-30	abc	./data_raw_all/8.9_4430_analog3_20200815-190815.jpg	ffffc3c783a7c7c1
+2024-03-30	abc	./data_raw_all/8.9_948cfd85cd30c97a931c75d74315dad2.jpg	ffff0e8787420d03
+2024-03-30	abc	./data_raw_all/8.9_analog2_20201003-081301.jpg	fefcdce4e0c08080
+2024-03-30	abc	./data_raw_all/8.9_analog3_20200928-135043.jpg	ffff4f27270a0000
+2024-03-30	abc	./data_raw_all/8.9_b8b1755cfa3dfd252ac71953bfe366cb.jpg	fffff9e0e4c0c1e3
+2024-03-30	abc	./data_raw_all/8.9_db13abd3f5d9ecc6b69e180ba94bbacc.jpg	ffbf0f8787420f07
+2024-03-30	abc	./data_raw_all/8.9_e8a550ffb623b35f2d596b7cc97ea4b0.jpg	ffffcec3c3464801
+2024-03-30	abc	./data_raw_all/9.0.jpg	ffdf4fc7c742bfbd
+2024-03-30	abc	./data_raw_all/9.0_022656a1cf941a762eecf00b88d23512.jpg	ffcfc74303071f0d
+2024-03-30	abc	./data_raw_all/9.0_113d922474dbae6e37c926892a084dd0.jpg	f9ecc6e0e0681f1e
+2024-03-30	abc	./data_raw_all/9.0_177bde29b3c60fecf33cd5538c4637f2.jpg	ffbf0f87c3420507
+2024-03-30	abc	./data_raw_all/9.0_1d6b122a315576d496eacebebca05492.jpg	f7dfc583c3e667d6
+2024-03-30	abc	./data_raw_all/9.0_228c1eeb80ae80571b5d11a38d3823ad.jpg	f7dfc5c3e3f2e77e
+2024-03-30	abc	./data_raw_all/9.0_28aafe323c02d0fbf039100b9152e57d.jpg	fcd8c0e0e0f0e0fc
+2024-03-30	abc	./data_raw_all/9.0_319d6814fc235d9fd09a5e213920de67.jpg	ffdfc6e0e0e0e0f0
+2024-03-30	abc	./data_raw_all/9.0_4422_zeiger4_2019-06-03T153009.jpg	f9dfc78703431b7d
+2024-03-30	abc	./data_raw_all/9.0_4433_zeiger1_2019-06-03T051009.jpg	ffffc783c0c0c030
+2024-03-30	abc	./data_raw_all/9.0_4473_zeiger3_2019-09-15_05-49-06.jpg	ffff4e83c342d7ff
+2024-03-30	abc	./data_raw_all/9.0_4474_zeiger3_2020-02-12_16-41-06.jpg	ffdf0607474699c7
+2024-03-30	abc	./data_raw_all/9.0_4482_zeiger4_2019-09-14_11-20-12.jpg	79dfcf87c3c3ffff
+2024-03-30	abc	./data_raw_all/9.0_4484_zeiger4_2019-11-19_01-12-03.jpg	ff8f4783e5ffbfff
+2024-03-30	abc	./data_raw_all/9.0_4485_zeiger4_2020-04-29_11-30-02.jpg	fcddc6c3e3e2dc15
+2024-03-30	abc	./data_raw_all/9.0_7291b974ffeb4529a25c1a612c4a99d6.jpg	bf9f470323470f27
+2024-03-30	abc	./data_raw_all/9.0_7fa1da6271aa21b508d6786f2d5df0aa.jpg	f7dfc5c3e1e2a77e
+2024-03-30	abc	./data_raw_all/9.0_839e27da7461bacae5d942fc67609fc2.jpg	fdcfc2c1e0e2f4f5
+2024-03-30	abc	./data_raw_all/9.0_a33a382f0fb721e2fc70684820eeab4c.jpg	a0c0c0c0e0f0f1fa
+2024-03-30	abc	./data_raw_all/9.0_b65560e24c3927bc340ef22aa8a773dd.jpg	0000073f7f7ffffc
+2024-03-30	abc	./data_raw_all/9.0_f31213c552ef33706af0e1bda7103309.jpg	fcce66e0effe3c80
+2024-03-30	abc	./data_raw_all/9.0_pointer_20211008-113653.jpg	fffdece0e0e0c0e0
+2024-03-30	abc	./data_raw_all/9.1_021a15b96a910316ca9fc037dfd6db0b.jpg	fdcec2e1e160f4f4
+2024-03-30	abc	./data_raw_all/9.1_23c33a4e722212a42c708ea6932a72fd.jpg	f7c5c5c3e2e7777d
+2024-03-30	abc	./data_raw_all/9.1_3b71244fb7902b977eff29feaa9c7481.jpg	0400033f3f7ffffe
+2024-03-30	abc	./data_raw_all/9.1_4.jpg	fcdcc4c0e0f0fcf0
+2024-03-30	abc	./data_raw_all/9.1_43482e91ac3ba02860be12d3e9f3e012.jpg	ffcf6783c3f36f3f
+2024-03-30	abc	./data_raw_all/9.1_4423_zeiger4_2019-06-03T183009.jpg	fedfc78703031b7d
+2024-03-30	abc	./data_raw_all/9.1_4493_analog2_20200817-231957.jpg	ffdfc782c326c1d7
+2024-03-30	abc	./data_raw_all/9.1_4508_zeiger1_2019-06-03T085009.jpg	ffdfc7c3c0c0c0b0
+2024-03-30	abc	./data_raw_all/9.1_4537_zeiger2_2019-11-19_09-22-03.jpg	ffcf8f87c5def8e0
+2024-03-30	abc	./data_raw_all/9.1_4566_zeiger4_2019-09-14_19-44-51.jpg	7edfcf87c3c3ffff
+2024-03-30	abc	./data_raw_all/9.1_4569_zeiger4_2020-04-29_11-23-02.jpg	f8dec6e3e3e2dc15
+2024-03-30	abc	./data_raw_all/9.1_4746f8282bf77b133a83039a93fec379.jpg	fbcfc6c0c0e2fcfd
+2024-03-30	abc	./data_raw_all/9.1_4d282bcff2db7825fa39e75531f7bb16.jpg	fcdecee7e63e3c00
+2024-03-30	abc	./data_raw_all/9.1_7c4634e387d5d509349b31607c039824.jpg	80c0c0c0e0f0f9f6
+2024-03-30	abc	./data_raw_all/9.1_7e7c557c9594debe56660337a46a5911.jpg	e9ee6661613f1f1f
+2024-03-30	abc	./data_raw_all/9.1_a51fa9ec434cfbffec87c59e1908b26c.jpg	fdcec2c1c1e2f6f4
+2024-03-30	abc	./data_raw_all/9.1_aeea66d7205870d48df759d542f43e25.jpg	ffcf4783e3e74f3f
+2024-03-30	abc	./data_raw_all/9.1_ana3_20220624-005203.jpg	ffcfc783a54ecb0c
+2024-03-30	abc	./data_raw_all/9.1_analog1_20201006-063830.jpg	f0f8e8e0e0f8e0c1
+2024-03-30	abc	./data_raw_all/9.1_d147e22665b64981492b18f3f1287482.jpg	f7cfe5c3e3e2e77e
+2024-03-30	abc	./data_raw_all/9.1_d2c4ad026e111d226a0554428d88a517.jpg	e9ee46e1653f1f0f
+2024-03-30	abc	./data_raw_all/9.1_f305aab69b8d2fda3cceb155e8c97c0c.jpg	e9ee66a1613f1f0f
+2024-03-30	abc	./data_raw_all/9.1_main_ana3_20221213-142934.jpg	ffffffe1c1000103
+2024-03-30	abc	./data_raw_all/9.2_1f769bb42f9b912ac3fb2810f4331e3b.jpg	040002273f7ffffe
+2024-03-30	abc	./data_raw_all/9.2_32c1e9d34f96b3aae90c1ddaee02cf77.jpg	bfcf470323278f27
+2024-03-30	abc	./data_raw_all/9.2_432b9556f796d3e96077f81c67aa3f6f.jpg	ede666e1613f1f1f
+2024-03-30	abc	./data_raw_all/9.2_4480_zeiger4_2019-06-02T111009.jpg	f9cfc78783031b7f
+2024-03-30	abc	./data_raw_all/9.2_4522_zeiger1_2019-06-03T111009.jpg	ffcfc7c1c0c0f0b0
+2024-03-30	abc	./data_raw_all/9.2_4564_zeiger3_2020-06-14_18-34-57.jpg	ffdf4fe7e75a0000
+2024-03-30	abc	./data_raw_all/9.2_4565_zeiger4_2019-06-06T131009.jpg	fcdec78783431f7d
+2024-03-30	abc	./data_raw_all/9.2_4567_zeiger4_2019-09-15_06-20-12.jpg	f9cf4f87c343ffff
+2024-03-30	abc	./data_raw_all/9.2_4573_analog4_20200821-014239.jpg	3f9f47078367cfef
+2024-03-30	abc	./data_raw_all/9.2_4584_zeiger2_2019-09-14_19-20-12.jpg	7ccec7c3e343dff7
+2024-03-30	abc	./data_raw_all/9.2_4600_zeiger2_2020-06-14_13-17-22.jpg	fdfcc8e4e0f0c080
+2024-03-30	abc	./data_raw_all/9.2_4602_zeiger3_2019-11-19_02-12-03.jpg	ffcfc787e7dfe800
+2024-03-30	abc	./data_raw_all/9.2_4607_zeiger4_2019-09-15_05-20-12.jpg	fccfcf87c343ffff
+2024-03-30	abc	./data_raw_all/9.2_4699_zeiger3_2019-11-19_18-12-04.jpg	ffcfc787e5df8800
+2024-03-30	abc	./data_raw_all/9.2_46e78987f8d6542f1c8e26523820a5a4.jpg	ffdf476307070f05
+2024-03-30	abc	./data_raw_all/9.2_61940b47b8edf6d800ead935e5194583.jpg	ffdf0f0747420507
+2024-03-30	abc	./data_raw_all/9.2_811f6dbc7cfcb9f9f71e93a845ac5986.jpg	ffcfc6c3c2e2fcb0
+2024-03-30	abc	./data_raw_all/9.2_8614c6dad3e1e63b993abaf7f26cc863.jpg	d5c1c4c1c2eff7ff
+2024-03-30	abc	./data_raw_all/9.2_9.2.jpg	9e1f4f87c747ff7f
+2024-03-30	abc	./data_raw_all/9.2_baa27d9780a24869ea9ea49e4769e4ad.jpg	bfcf470323478f67
+2024-03-30	abc	./data_raw_all/9.2_d422714c6ddec154230d34c32e520b44.jpg	80c0e0c0e0f0f0f2
+2024-03-30	abc	./data_raw_all/9.2_main_ana3_20221213-142434.jpg	ffffffe1c0008183
+2024-03-30	abc	./data_raw_all/9.2_pointer_20211022-060300.jpg	fffdece0e0c080c0
+2024-03-30	abc	./data_raw_all/9.3_37c3d6adc3cdfaf0119b6feb597ed370.jpg	f7c7e583c3e667d6
+2024-03-30	abc	./data_raw_all/9.3_42726e503d98fb5ba277158e08c58b06.jpg	fdcfe6c1e0e2dcd0
+2024-03-30	abc	./data_raw_all/9.3_4613_zeiger4_2020-04-29_13-18-02.jpg	fccfc6e3e3e2dc15
+2024-03-30	abc	./data_raw_all/9.3_4632_zeiger1_2020-06-14_11-42-40.jpg	f0e8e8e4e4f8c081
+2024-03-30	abc	./data_raw_all/9.3_65d411ed2a999f5006a658f340ba861d.jpg	ffffffe0c484c163
+2024-03-30	abc	./data_raw_all/9.3_7828b99d31eadb1fd2df69ec736d8557.jpg	fffff9e4a69c8000
+2024-03-30	abc	./data_raw_all/9.3_919e154ecbf3b83604bb424a0e748c69.jpg	dfcf470323478f6f
+2024-03-30	abc	./data_raw_all/9.3_a0952b7fcfb807eca24931409c7e287b.jpg	9fcf470303070504
+2024-03-30	abc	./data_raw_all/9.3_c5c6ff7c7ab7d35d0ecc001225b0fd9e.jpg	ffcfc6c3c3464000
+2024-03-30	abc	./data_raw_all/9.3_c7a6d03ac6cc878b554a707d73a7a2a2.jpg	feef67a3c1f36f3f
+2024-03-30	abc	./data_raw_all/9.4_0b71b3ad25d314816e7ac8eccbc8111a.jpg	fcee66e0eeff1c80
+2024-03-30	abc	./data_raw_all/9.4_26b3334236f43cd1b56dd96ddbbf4c6a.jpg	ffe7c3c09cf8c000
+2024-03-30	abc	./data_raw_all/9.4_2a2891530d9b1ed3f14dc5390ab017d8.jpg	ffcf4f0303030f05
+2024-03-30	abc	./data_raw_all/9.4_3a250eaa40e18b4f19408abe578dabbc.jpg	ffffff8785808001
+2024-03-30	abc	./data_raw_all/9.4_4576_zeiger1_2019-06-03T123009.jpg	ffefc7c1c0c0c0b0
+2024-03-30	abc	./data_raw_all/9.4_4688_zeiger2_2020-04-29_13-34-02.jpg	ffedc6a0e0e090c0
+2024-03-30	abc	./data_raw_all/9.4_4703_zeiger3_2020-04-29_11-18-02.jpg	ffcfc6c2c3429881
+2024-03-30	abc	./data_raw_all/9.4_4705_zeiger3_2020-06-15_01-06-00.jpg	ffcf6fe7e75e0000
+2024-03-30	abc	./data_raw_all/9.4_4729_zeiger4_2020-04-29_10-47-26.jpg	feccc6e3e3e2dc15
+2024-03-30	abc	./data_raw_all/9.4_4751_zeiger2_2019-09-15_05-40-13.jpg	7dcfc7a3c342dfff
+2024-03-30	abc	./data_raw_all/9.4_4764_zeiger3_2019-11-19_18-32-04.jpg	efcfc787e7dfc880
+2024-03-30	abc	./data_raw_all/9.4_48b60f4285201a4346ef9266bf34d423.jpg	ffffffc780800101
+2024-03-30	abc	./data_raw_all/9.4_864cdfdb19a3d46126e95b259bf498d1.jpg	fceeeee6e63e1c20
+2024-03-30	abc	./data_raw_all/9.4_9.1.jpg	ffefe7e2e0e0c8c0
+2024-03-30	abc	./data_raw_all/9.4_aeb72af3213494c0a88629f2b3a60647.jpg	ffcfc7c3c3c65a04
+2024-03-30	abc	./data_raw_all/9.4_ana4_20220626-110214.jpg	ffcf4783233f1f07
+2024-03-30	abc	./data_raw_all/9.4_analog2_20200925-194829.jpg	fffcece4e0d08080
+2024-03-30	abc	./data_raw_all/9.4_c764a2f883897faee9e300df5cc82a8d.jpg	ffe76783c3e36f3f
+2024-03-30	abc	./data_raw_all/9.4_caa10d6d51e584eb154de8762db0aea5.jpg	ffc76783e3e75f3f
+2024-03-30	abc	./data_raw_all/9.4_e2694e4ad0778aaf8d1c08fa2de4a81d.jpg	ffffefc784808101
+2024-03-30	abc	./data_raw_all/9.5.jpg	ffcf4fc7c742bfbb
+2024-03-30	abc	./data_raw_all/9.5_0754f0633b1029adba555bff01918f45.jpg	ffff4f07c7020703
+2024-03-30	abc	./data_raw_all/9.5_07fe020e1f2f6e115d3af04d656d0b04.jpg	ffcfc7e0e0e0c0c0
+2024-03-30	abc	./data_raw_all/9.5_29681542289faa69719c8a0328e3924e.jpg	fcee6660ecfe1c80
+2024-03-30	abc	./data_raw_all/9.5_33e7c566e95c93fedc1db35c43c77d3c.jpg	ffcf4f8787020f07
+2024-03-30	abc	./data_raw_all/9.5_4609_zeiger4_2019-11-19_13-22-03.jpg	cfcf4783e37f9fff
+2024-03-30	abc	./data_raw_all/9.5_4610_zeiger4_2019-11-19_13-27-03.jpg	efcf47a3e3ffbfff
+2024-03-30	abc	./data_raw_all/9.5_4706_zeiger4_2019-06-01T202014.jpg	f9cfc78703431f1f
+2024-03-30	abc	./data_raw_all/9.5_4709_zeiger4_2019-11-19_13-12-03.jpg	cfcf47a3e3ffdfff
+2024-03-30	abc	./data_raw_all/9.5_4730_analog2_20200820-184826.jpg	ffc7c786c3a6c1d7
+2024-03-30	abc	./data_raw_all/9.5_4766_zeiger4_2019-06-01T164011.jpg	fecfc78703431f1f
+2024-03-30	abc	./data_raw_all/9.5_4774_analog4_20200815-112210.jpg	bfcf4703a367dff7
+2024-03-30	abc	./data_raw_all/9.5_4776_zeiger2_2019-11-19_00-02-02.jpg	efcfcf87c5def8f0
+2024-03-30	abc	./data_raw_all/9.5_4777_zeiger2_2020-06-16_17-03-11.jpg	fdecece4e0f0c080
+2024-03-30	abc	./data_raw_all/9.5_9.4.jpg	fcece4e0e0f0fcf0
+2024-03-30	abc	./data_raw_all/9.5_bdeab982fbac878494bf669d45b91020.jpg	ffefe7e3e3fffc3c
+2024-03-30	abc	./data_raw_all/9.5_d55e803263c6b358a69ee10b3dc898ec.jpg	ff9f4f0787060f03
+2024-03-30	abc	./data_raw_all/9.6.jpg	ffefe7e2e0c0d0c0
+2024-03-30	abc	./data_raw_all/9.6_00a320ca9ef2a27c49120be5b580719e.jpg	ffff4f07c3060301
+2024-03-30	abc	./data_raw_all/9.6_05cca84766f8de102f2f0e5419350e63.jpg	fdcfc7e3c3e2d4b4
+2024-03-30	abc	./data_raw_all/9.6_42f3c253da9905bb66b3a238e4a79d7c.jpg	f1e6e6e1613f1f1f
+2024-03-30	abc	./data_raw_all/9.6_4800_zeiger3_2020-06-16_19-24-22.jpg	ffefefe7675a0000
+2024-03-30	abc	./data_raw_all/9.6_4806_zeigeru__2019-06-02T10500.jpg	fdeec7e1c140c0c0
+2024-03-30	abc	./data_raw_all/9.6_4907_analog4_20200812-223536.jpg	af474783a3cfcff7
+2024-03-30	abc	./data_raw_all/9.6_5b046ded88310f7bd0425368ef2ac2e4.jpg	fdefc7e1c1e0d4b4
+2024-03-30	abc	./data_raw_all/9.6_65c660d48d3bd177fb4fe8ddad96f99f.jpg	ffcf4f87c7420d03
+2024-03-30	abc	./data_raw_all/9.6_a5b7870797689116ff66b72e84f41243.jpg	878f470303070f17
+2024-03-30	abc	./data_raw_all/9.6_aa1fa04bc803ba225a29218a10530731.jpg	efefe76307071f07
+2024-03-30	abc	./data_raw_all/9.6_ana2_20220626-001213.jpg	efcfc787c346cba4
+2024-03-30	abc	./data_raw_all/9.6_analog3_20201030-202141.jpg	ffef6f27271a0000
+2024-03-30	abc	./data_raw_all/9.6_c2996bad7feda226091a541b5927397b.jpg	fffffee08481c1e3
+2024-03-30	abc	./data_raw_all/9.6_cd86b45ff0c0511886b07703c594b39d.jpg	edc6e2e1e0e0f4f4
+2024-03-30	abc	./data_raw_all/9.6_d511392e0d657a473c78c689630d43c1.jpg	0f0f2703031f1f3f
+2024-03-30	abc	./data_raw_all/9.6_e512bcc089d7453275d0288df1e3749a.jpg	edc6c2e1c162fef4
+2024-03-30	abc	./data_raw_all/9.6_main_ana3_20221214-174621.jpg	ffffffe080008103
+2024-03-30	abc	./data_raw_all/9.6_pointer_20211023-052841.jpg	fffde6e4e08080c0
+2024-03-30	abc	./data_raw_all/9.7_0cb925e2431e0c09158df561afbb07c8.jpg	ffcf6f2303030704
+2024-03-30	abc	./data_raw_all/9.7_2cf03a7ee1054c9c21ba02215b6e9a91.jpg	f7e7e583c3e6eff6
+2024-03-30	abc	./data_raw_all/9.7_3df56015746f08da4a6eaf85acbdb9e1.jpg	fcece6e6e67c3040
+2024-03-30	abc	./data_raw_all/9.7_4833_zeiger2_2019-06-01T203011.jpg	fde6c7e1c040f0e0
+2024-03-30	abc	./data_raw_all/9.7_4878_zeigeru__2019-06-05T06300.jpg	ffefc781c1c040b4
+2024-03-30	abc	./data_raw_all/9.7_68f4aa7494a8904b5343fca3536f7ff0.jpg	044400207ffffffe
+2024-03-30	abc	./data_raw_all/9.7_7869e09b27854cc5cf0b022014e46f35.jpg	ece666e0e8fe3e98
+2024-03-30	abc	./data_raw_all/9.7_810ab5a789373bc1f47d93b27b1b84e3.jpg	ffffffe4a43c8000
+2024-03-30	abc	./data_raw_all/9.7_94e5a2fab73bcf6f0c36b28fb9ecedc2.jpg	c5e5e2c0c2eff7ff
+2024-03-30	abc	./data_raw_all/9.7_a2e15ed8d209b46367771117af85557b.jpg	ffefc6c4e0e0f0e0
+2024-03-30	abc	./data_raw_all/9.7_d2061508e63bf8c7dea1acd77d528114.jpg	fdefe6e3c3e2d4b4
+2024-03-30	abc	./data_raw_all/9.7_f5eb8e3f4735293d84f38a403910289e.jpg	ffcfe7e1e0c0c8c0
+2024-03-30	abc	./data_raw_all/9.8_166942e23d29eef618f47437c736d6d8.jpg	ffa7670303030704
+2024-03-30	abc	./data_raw_all/9.8_4906_analog3_20200820-181642.jpg	ffe7e7c383c2cbd5
+2024-03-30	abc	./data_raw_all/9.8_4926_zeiger2_2020-02-17_17-43-42.jpg	ffcf66c7c64699e3
+2024-03-30	abc	./data_raw_all/9.8_5a1aad41da47172b789d2093ef1af9fb.jpg	f7e6e1c3e3e2e7fe
+2024-03-30	abc	./data_raw_all/9.8_773cf78ad2d6c74f86b0ef92e8fa3825.jpg	ffef6763070f0f03
+2024-03-30	abc	./data_raw_all/9.8_781dc0d6ef4bf61bd43026e0a1a52056.jpg	fce66661ecfe3c80
+2024-03-30	abc	./data_raw_all/9.8_a4646837ec0ef966cb615d0e83a80ff7.jpg	ffefe6e3c3625000
+2024-03-30	abc	./data_raw_all/9.8_adc4d1b3806051194924389d902c84fb.jpg	e5e7e2e1e0e2f4f5
+2024-03-30	abc	./data_raw_all/9.8_ana4_20220628-005723.jpg	efe747a3231f1f17
+2024-03-30	abc	./data_raw_all/9.9.jpg	ffe7e7e2c0c0d1c1
+2024-03-30	abc	./data_raw_all/9.9_0001_analog1_20200814-090613.jpg	97e5e3c2c2efe5f7
+2024-03-30	abc	./data_raw_all/9.9_1293b1e49336c113752bb344b2d557ff.jpg	bfaf670307070504
+2024-03-30	abc	./data_raw_all/9.9_315603db044a1328cb5f8a094aed599b.jpg	ffcf4fa7c3420507
+2024-03-30	abc	./data_raw_all/9.9_3c12d2b62090685521aeb3e1c9fa645f.jpg	ffffffe08081c1f7
+2024-03-30	abc	./data_raw_all/9.9_4934_zeiger4_2019-06-06T015009.jpg	feeec78783431f7f
+2024-03-30	abc	./data_raw_all/9.9_4a8b4e2c4f64e6079c7a84e0f6bceaf0.jpg	fde7e7e1c1e2d4b4
+2024-03-30	abc	./data_raw_all/9.9_4cb559d572ab1e26e32cb20bcfd590e0.jpg	ffcf4ea7c7420503
+2024-03-30	abc	./data_raw_all/9.9_5b2d5738711c040f132a0a939d2db997.jpg	efe7c72323478f27
+2024-03-30	abc	./data_raw_all/9.9_786bbba34d96f575e8adf915db8d72fc.jpg	f1f2e6e1612f1f1f
+2024-03-30	abc	./data_raw_all/9.9_8fc8e279012dcde2b7556ce8871a8cec.jpg	f4f666e3e8fe3c80
+2024-03-30	abc	./data_raw_all/9.9_a40c326a3dc5431543ae410648c50288.jpg	ffe7e6c4c0e0f0e0
+2024-03-30	abc	./data_raw_all/9.9_bba3e8309811f376c5c087bc57bc9763.jpg	efefe7e3e0c0d8c0
+2024-03-30	abc	./data_raw_all/9.9_cd0ec96bd0825a9fd05d157210d9a2ab.jpg	ffffffe08084c173
+2024-03-30	abc	./data_raw_all/9.9_fe08392177e40ab31a8be71885765c1a.jpg	ffff4f27c3420703
diff --git a/requirements.txt b/requirements.txt
index f1969b18..1c3c10a5 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,4 +6,5 @@ scikit-learn
 pandas
 tensorflow >= 2.10
 tensorflow-model-optimization
-opencv-python
\ No newline at end of file
+opencv-python
+imagehash
\ No newline at end of file
diff --git a/test/fingerprint.pb b/test/fingerprint.pb
new file mode 100644
index 00000000..f19b060e
--- /dev/null
+++ b/test/fingerprint.pb
@@ -0,0 +1 @@
+�������ă
񸩙�ݍ�Ӗ�������
 쐽�����(���ʵ����
2

\ No newline at end of file
diff --git a/test/saved_model.pb b/test/saved_model.pb
new file mode 100644
index 00000000..9865594c
Binary files /dev/null and b/test/saved_model.pb differ
diff --git a/test/variables/variables.data-00000-of-00001 b/test/variables/variables.data-00000-of-00001
new file mode 100644
index 00000000..fb7137c6
Binary files /dev/null and b/test/variables/variables.data-00000-of-00001 differ
diff --git a/test/variables/variables.index b/test/variables/variables.index
new file mode 100644
index 00000000..a9d5cae7
Binary files /dev/null and b/test/variables/variables.index differ