mnist_conv.py

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data

batch_size = 128
test_size = 1000
net_name = 'conv_net_3x3'

def init_weights(shape):
    return tf.Variable(tf.random_normal(shape, stddev=0.01))


def model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden):
    l1a = tf.nn.relu(tf.nn.conv2d(X, w,                       # l1a shape=(?, 28, 28, 32)
                        strides=[1, 1, 1, 1], padding='SAME'))
    l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1],              # l1 shape=(?, 14, 14, 32)
                        strides=[1, 2, 2, 1], padding='SAME')
    l1 = tf.nn.dropout(l1, p_keep_conv)

    l2a = tf.nn.relu(tf.nn.conv2d(l1, w2,                     # l2a shape=(?, 14, 14, 64)
                        strides=[1, 1, 1, 1], padding='SAME'))
    l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1],              # l2 shape=(?, 7, 7, 64)
                        strides=[1, 2, 2, 1], padding='SAME')
    l2 = tf.nn.dropout(l2, p_keep_conv)

    l3a = tf.nn.relu(tf.nn.conv2d(l2, w3,                     # l3a shape=(?, 7, 7, 128)
                        strides=[1, 1, 1, 1], padding='SAME'))
    l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1],              # l3 shape=(?, 4, 4, 128)
                        strides=[1, 2, 2, 1], padding='SAME')
    l3 = tf.reshape(l3, [-1, w4.get_shape().as_list()[0]])    # reshape to (?, 2048)
    l3 = tf.nn.dropout(l3, p_keep_conv)

    l4 = tf.nn.relu(tf.matmul(l3, w4))
    l4 = tf.nn.dropout(l4, p_keep_hidden)

    pyx = tf.matmul(l4, w_o)
    return pyx

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
trX = trX.reshape(-1, 28, 28, 1)  # 28x28x1 input img
teX = teX.reshape(-1, 28, 28, 1)  # 28x28x1 input img

X = tf.placeholder("float", [None, 28, 28, 1])
Y = tf.placeholder("float", [None, 10])

w = init_weights([3, 3, 1, 32])       # 3x3x1 conv, 32 outputs
w2 = init_weights([3, 3, 32, 64])     # 3x3x32 conv, 64 outputs
w3 = init_weights([3, 3, 64, 128])    # 3x3x32 conv, 128 outputs
w4 = init_weights([128 * 4 * 4, 625]) # FC 128 * 4 * 4 inputs, 625 outputs
w_o = init_weights([625, 10])         # FC 625 inputs, 10 outputs (labels)

p_keep_conv = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(py_x, Y))
train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)

prec = tf.reduce_mean(tf.cast(tf.equal(predict_op, tf.argmax(Y, 1)), tf.float32))

summary_cost = tf.scalar_summary('cost', cost)
summary_prec = tf.scalar_summary('prec', prec)

train_writer = tf.train.SummaryWriter("logs/" + net_name + "/train", flush_secs=5)
test_writer = tf.train.SummaryWriter("logs/" + net_name + "/test", flush_secs=5)

sav = tf.train.Saver()

# Launch the graph in a session
with tf.Session() as sess:
    # you need to initialize all variables
    tf.initialize_all_variables().run()

    k = 1
    for i in range(100):
        training_batch = zip(range(0, len(trX), batch_size),
                             range(batch_size, len(trX)+1, batch_size))
        for start, end in training_batch:
            log_cost, log_prec, val_prec, _ = sess.run([summary_cost, summary_prec, prec, train_op], feed_dict={X: trX[start:end], Y: trY[start:end],
                                          p_keep_conv: 0.8, p_keep_hidden: 0.5})
            train_writer.add_summary(log_cost, k)
            train_writer.add_summary(log_prec, k)
            print(i, k, "train prec", val_prec)
            k = k + 1

        log_prec, val_prec = sess.run([summary_prec,prec], feed_dict={X: teX[:test_size],
                                                                      Y: teY[:test_size],
                                                                      p_keep_conv: 1.0,
                                                                      p_keep_hidden: 1.0})
        test_writer.add_summary(log_prec, k)
        print(i, val_prec)
        sav.save(sess, "checkpoints/" + net_name, global_step = i)