-
自编码网络的作用是,将输入样本压缩到隐藏层(隐藏层神经元个数小于输入层),再在输出端重建样本。也就是说,自编码网络输出层与输入层存在如下关系:
-
注意:由于神经元的输出只在0和1之间,因此输入需要进行均值归一化
自编码网络可以看做将数据进行压缩(由原来的“n-维”压缩成“m维”(m=隐藏层神经元数目)),然后再在需要的时候用损失尽量小的方式将数据恢复出来。
这里有两层意思:
第一,自编码网络是要将经过压缩的数据还原
第二,还原数据应该使得损失尽量小
from __future__ import division, print_function, absolute_import
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
# 下载并导入MNIST数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 参数
learning_rate = 0.01#学习率
training_epochs = 20#训练的周期
batch_size = 256#每一批次训练的大小
display_step = 1
examples_to_show = 10
# 神经网络的参数
n_hidden_1 = 256 # 隐层1的神经元个数
n_hidden_2 = 128 # 隐层2神经元个数
n_input = 784 # MNIST数据集的输出(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']))
# 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
# Building the decoder
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
# 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.global_variables_initializer()
sess = tf.InteractiveSession()
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()