18-Day7.md

BDMI --第七周学习小结

赵子瑜

本周课程的主要内容有：

1. 即刻执行

   C，Java，Python都用了即刻求值.

   tensorflow2 默认使用了eager execution

2. 模型的训练与评估

   训练数据的加载：

   (x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
   x_train = x_train.reshape(60000, 784).astype('float32') / 255
   x_test = x_test.reshape(10000, 784).astype('float32') / 255
   

   模型的构造：

   inputs = keras.Input(shape=(784,), name="digits")
   x = layers.Dense(512, activation="relu", name="dense_1")(inputs)
   x = layers.Dense(128, activation="relu", name="dense_2")(x)
   outputs = layers.Dense(10, activation="softmax", name="predictions")(x)
   model = keras.Model(inputs=inputs, outputs=outputs)
   

   编译：

   model.compile(
       optimizer="adam",
       loss="sparse_categorical_crossentropy",
       metrics=["sparse_categorical_accuracy"],
   )
   

   训练模型：

   history = model.fit(
      x_train,
       y_train,
       batch_size=1024,
       epochs=10,
       validation_data=(x_val, y_val),
   )