TensorFlow-Examples/examples/3 - Neural Networks/autoencoder.py

# -*- coding: utf-8 -*-

""" Auto Encoder Example.
Using an auto encoder on MNIST handwritten digits.
References:
    Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based
    learning applied to document recognition." Proceedings of the IEEE,
    86(11):2278-2324, November 1998.
Links:
    [MNIST Dataset] http://yann.lecun.com/exdb/mnist/
"""
from __future__ import division, print_function, absolute_import

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

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

# Parameters
learning_rate = 0.01
training_epochs = 20
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)

y_pred = decoder_op
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)
            # Fit training using batch data
            _, cost_value = 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(cost_value))

    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()

# # Regression, with mean square error
# net = tflearn.regression(decoder, optimizer='adam', learning_rate=0.001,
#                          loss='mean_square', metric=None)
#
# # Training the auto encoder
# model = tflearn.DNN(net, tensorboard_verbose=0)
# model.fit(X, X, n_epoch=10, validation_set=(testX, testX),
#           run_id="auto_encoder", batch_size=256)
#
# # Encoding X[0] for test
# print("\nTest encoding of X[0]:")
# # New model, re-using the same session, for weights sharing
# encoding_model = tflearn.DNN(encoder, session=model.session)
# print(encoding_model.predict([X[0]]))
#
# # Testing the image reconstruction on new data (test set)
# print("\nVisualizing results after being encoded and decoded:")
# testX = tflearn.data_utils.shuffle(testX)[0]
# # Applying encode and decode over test set
# encode_decode = model.predict(testX)
# # Compare original images with their reconstructions
# f, a = plt.subplots(2, 10, figsize=(10, 2))
# for i in range(10):
#     a[0][i].imshow(np.reshape(testX[i], (28, 28)))
#     a[1][i].imshow(np.reshape(encode_decode[i], (28, 28)))
# f.show()
# plt.draw()
# plt.waitforbuttonpress()