自编码器(Autoencoder):使用无监督方法,通过自身高阶特征编码自己,是一种输入和输出“基本一致”的神经网络。
自编码器使用少量稀疏的高阶特征重构输出,同时附加限制:
1)如果限制中间隐藏层节点数量,使得中间层节点数量小于输入\输出节点数量,则为降维过程;如果给中间层加L1正则,则可根据惩罚系数控制中间层节点稀疏程度,惩罚系数越大,特征组合越稀疏,特征数量越少。
2)如果给数据加入噪声,则为去噪自编码器(Denoizing Autoencoder),模型将从噪声中学习数据特征。
自编码器的用途(function):
1)去噪
2)降维
代码实现:
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#import mnist data sets
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot = False)
#define parameters
learning_rate = 0.001
training_epochs = 10
batch_size = 256
display_step = 1
examples_to_show = 10
n_input = 784
#tf graph input(mnist picture)
X = tf.placeholder('float', [None, n_input])
#number of parameters in hidden layer
n_hidden_1 = 256
n_hidden_2 = 128
#create the weights and biases dict for encoder and decoder
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])),
}
#define encoder
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
#define decoder
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
#build model
encoder_op = encoder(X)
decoder_op = decoder(encoder_op)
#define prediction
y_pred = decoder_op
y_true = X
#define cost function and optimizer
cost = tf.reduce_mean(tf.pow((y_true - y_pred),2))
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)
#optimization and display results
with tf.Session() as sess:
#initialize variables
init = tf.global_variables_initializer()
sess.run(init)
total_batch = int(mnist.train.num_examples / batch_size)
for eoch 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 eoch % display_step == 0:
print("Eoch : ", '%04d' %(eoch + 1), "Cost = ", "{:.9f}".format(c))
print("optimization finished !")
#plot soure and result image
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)))
plt.show()
practice makes perfect!