加载模型
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./MNIST_data/", one_hot=True)
构建模型
learning_rate = 0.001
training_epochs = 20
batch_size = 256
display_step = 1
还要设置其他格数变量,表示从测试集中选择 10 张图片去验证自动编码器的结果
examples_to_show = 10
随后初始化权重与定义格络结构。我们设计这个自动编码格络含有两个隐藏层,第一个隐藏层神经元为 256 个,第二个隐藏层神经元为 128 个,定义网络参数如下:
n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784
然后定义输入数据,这里是无监督学习,所以只需要输入图片数据,不需要标记数据
X = tf.placeholder("float", [None, n_input])
初始化每一层的权重和偏置,如下
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])),
}
接着,定义自动编码模型的格络结构,包括压缩和解压两个过程:
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)
接着,我们构建损失函数和优化器,这里的损失函数用“最小二乘法”对原始数据集和输出的数据集进行平格差并取均值运算;优化器采用 RMSPropOptimizer
# 得出预测值
y_pred = decoder_op
# 得出真实值,即输入值
y_true = X
# 定义损失函数和优化器
cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2))
optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(cost)
训练数据及评估模型
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()