小白学Tensorflow之自编码Autoencoder

作者：chen_h
微信号 & QQ：862251340
微信公众号：coderpai

---

Autoencoder（自编码）是一种非监督学习算法，如下图，就是一个简单的自编码神经网络结构。

为了得到图中的W0，我们需要增加Layer2层，来进行训练，输出层为y=x。也就是说，网络的输出和输入是同一个结果。其中，Layer0层到Layer1层是一个编码过程encoder。Layer1层到Layer2层是一个解码过程decoder。通过这两个过程，Autoencoder可以将一个高维的数据编码成一个低维数据，这个操作在分类等问题中非常有用。

接下来，我们来具体学习怎么实现一个简单的Autoencoder。自编码神经网络和一般的神经网络结构差不多（简单来讲，虽然这种表示不正确，但是利于学习），我们也设计一个全连接神经网络，只是其中把神经网络分成了两部分，前一部分是一个编码器，后一部分是一个解码器。

第一，我们设计一个编码器。

def encoder(x):
    # Encoder Hidden layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),
                                   biases['encoder_b1']))
    # Encoder Hidden layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),
                                   biases['encoder_b2']))
    return layer_2

第二，我们设计一个解码器。

def decoder(x):
    # Decoder Hidden layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),
                                   biases['decoder_b1']))
    # Decoder Hidden layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),
                                   biases['decoder_b2']))
    return layer_2

完整代码，如下：

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from __future__ import division, print_function, absolute_import

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

# Import MINST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./tmp/data/", one_hot=True)

# Parameters
learning_rate = 0.01
training_epochs = 100
batch_size = 256
display_step = 1
examples_to_show = 10

# Network Parameters
n_hidden_1 = 256 # 1st layer num features
n_hidden_2 = 128 # 2nd layer num features
n_input = 784 # MNIST data input (img shape: 28*28)

# tf Graph input (only pictures)
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])),
}


# Building the encoder
def encoder(x):
    # Encoder Hidden layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),
                                   biases['encoder_b1']))
    # Decoder Hidden layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),
                                   biases['encoder_b2']))
    return layer_2


# Building the decoder
def decoder(x):
    # Encoder Hidden layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),
                                   biases['decoder_b1']))
    # Decoder Hidden layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),
                                   biases['decoder_b2']))
    return layer_2

# Construct model
encoder_op = encoder(X)
decoder_op = decoder(encoder_op)

# Prediction
y_pred = decoder_op
# Targets (Labels) are the input data.
y_true = X

# Define loss and optimizer, minimize the squared error
cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2))
optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(cost)

# Initializing the variables
init = tf.initialize_all_variables()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    total_batch = int(mnist.train.num_examples/batch_size)
    # Training cycle
    for epoch in range(training_epochs):
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={X: batch_xs})
        # Display logs per epoch step
        if epoch % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1),
                  "cost=", "{:.9f}".format(c))

    print("Optimization Finished!")

    # Applying encode and decode over test set
    encode_decode = sess.run(
        y_pred, feed_dict={X: mnist.test.images[:examples_to_show]})

    # Compare original images with their reconstructions
    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()