In [12]:

    

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import matplotlib.pyplot as plt


    

In [2]:

    

# 导入数据
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)


    

    




Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

In [15]:

    

# Parameter
learning_rate = 0.01
training_epochs = 10
batch_size = 256
display_step = 1
examples_to_show = 10


    

In [16]:

    

# Network Parameters
n_input = 784  # MNIST data input (img shape: 28*28)


    

In [17]:

    

# hidden layer settings
n_hidden_1 = 256 # 1st layer num features
n_hidden_2 = 128 # 2nd layer num features
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])),
    }


    

In [18]:

    

# 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


    

In [19]:

    

X = tf.placeholder(tf.float32, [None, n_input])
# Construct model
encoder_op = encoder(X) # 128 Features
decoder_op = decoder(encoder_op) # 784 Features

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


    

In [20]:

    

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


    

In [21]:

    

# Launch the graph
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    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)  # max(x) = 1, min(x) = 0
            # 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: %03d' % (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)))
    plt.show()


    

    




Epoch: 0001 cost= 0.080996707
Epoch: 0002 cost= 0.068300098
Epoch: 0003 cost= 0.063518345
Epoch: 0004 cost= 0.061104998
Epoch: 0005 cost= 0.057478067
Epoch: 0006 cost= 0.056752883
Epoch: 0007 cost= 0.057394233
Epoch: 0008 cost= 0.053765357
Epoch: 0009 cost= 0.054702699
Epoch: 0010 cost= 0.055206224
Optimization Finished!






    

In [ ]: