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_importimport tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltfrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data", one_hot=True)learning_rate = 0.01training_epochs = 20batch_size = 256display_step = 1examples_to_show = 10n_hidden_1 = 256n_hidden_2 = 128n_input = 784X = 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_2def 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_2encoder_op = encoder(X)decoder_op = decoder(encoder_op)y_pred = decoder_opy_true = Xcost = 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= 0.196800113Epoch: 0002 cost= 0.169325382Epoch: 0003 cost= 0.155912638Epoch: 0004 cost= 0.148683071Epoch: 0005 cost= 0.142708376Epoch: 0006 cost= 0.136180028Epoch: 0007 cost= 0.130748138Epoch: 0008 cost= 0.125925466Epoch: 0009 cost= 0.122442275Epoch: 0010 cost= 0.117254384Epoch: 0011 cost= 0.114797853Epoch: 0012 cost= 0.112438530Epoch: 0013 cost= 0.109801762Epoch: 0014 cost= 0.107820347Epoch: 0015 cost= 0.105974235Epoch: 0016 cost= 0.105912112Epoch: 0017 cost= 0.104165390Epoch: 0018 cost= 0.100365378Epoch: 0019 cost= 0.100399643Epoch: 0020 cost= 0.099709332Optimization 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。