深度自编码器python实现

深度自编码器的原理上一节已经讲过，这次我们来看一下它的python代码实现，这是基于mnist的自编码实现。

from __future__ import division, print_function, absolute_import

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)


learning_rate = 0.01
training_epochs = 20
batch_size = 256
display_step = 1
examples_to_show = 10


n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784


X = tf.placeholder("float", [None, n_input])

weights = {
    'encoder_h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'encoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'decoder_h1': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_1])),
    'decoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_input])),
}
biases = {
    'encoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'encoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'decoder_b2': tf.Variable(tf.random_normal([n_input])),
}



def encoder(x):

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),
                                   biases['encoder_b1']))

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),
                                   biases['encoder_b2']))
    return layer_2



def decoder(x):

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),
                                   biases['decoder_b1']))

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),
                                   biases['decoder_b2']))
    return layer_2


encoder_op = encoder(X)
decoder_op = decoder(encoder_op)


y_pred = decoder_op

y_true = X


cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2))
optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(cost)

init = tf.global_variables_initializer()


with tf.Session() as sess:
    sess.run(init)
    total_batch = int(mnist.train.num_examples/batch_size)

    for epoch in range(training_epochs):

        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)

            _, c = sess.run([optimizer, cost], feed_dict={X: batch_xs})

        if epoch % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1),
                  "cost=", "{:.9f}".format(c))

    print("Optimization Finished!")


    encode_decode = sess.run(
        y_pred, feed_dict={X: mnist.test.images[:examples_to_show]})

    f, a = plt.subplots(2, 10, figsize=(10, 2))
    for i in range(examples_to_show):
        a[0][i].imshow(np.reshape(mnist.test.images[i], (28, 28)))
        a[1][i].imshow(np.reshape(encode_decode[i], (28, 28)))
    f.show()
    plt.draw()
plt.waitforbuttonpress()

经过20次的迭代，我们的输出结果cost明显的减小了
Epoch: 0001 cost= 0.196800113
Epoch: 0002 cost= 0.169325382
Epoch: 0003 cost= 0.155912638
Epoch: 0004 cost= 0.148683071
Epoch: 0005 cost= 0.142708376
Epoch: 0006 cost= 0.136180028
Epoch: 0007 cost= 0.130748138
Epoch: 0008 cost= 0.125925466
Epoch: 0009 cost= 0.122442275
Epoch: 0010 cost= 0.117254384
Epoch: 0011 cost= 0.114797853
Epoch: 0012 cost= 0.112438530
Epoch: 0013 cost= 0.109801762
Epoch: 0014 cost= 0.107820347
Epoch: 0015 cost= 0.105974235
Epoch: 0016 cost= 0.105912112
Epoch: 0017 cost= 0.104165390
Epoch: 0018 cost= 0.100365378
Epoch: 0019 cost= 0.100399643
Epoch: 0020 cost= 0.099709332
Optimization Finished!
通过观察最后的图像特征，经过自编码后的图片与原始的输入非常的相似，只是多了一些噪声在原始的图片上。cost的值也降到了0.1一下，cost值
还可以通过调节参数来让其继续减小。