Autoencoder.py

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

# Load the data
mnist = input_data.read_data_sets('MNIST/', one_hot=True)

# Setting up Parameters
learning_rate = 0.001
training_epochs = 30
batch_size = 256
display_step = 5

# Network parameters
n_hidden_1 = 256  # 1st Layer num features
n_hidden_2 = 128  # 2nd Layer num features
n_hidden_3 = 64  # 3rd Layer num features
n_input = 784  # MNIST data input (img shape: 28*23)

# TensorFlow Graph input
X = tf.placeholder(tf.float32, [None, n_input])

# Declare weights and biases for each hidden layer
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])),
    'encoder_h3': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_3])),
    'decoder_h1': tf.Variable(tf.random_normal([n_hidden_3, n_hidden_2])),
    'decoder_h2': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_1])),
    'decoder_h3': 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])),
    'encoder_b3': tf.Variable(tf.random_normal([n_hidden_3])),
    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_2])),
    'decoder_b2': tf.Variable(tf.random_normal([n_hidden_1])),
    'decoder_b3': tf.Variable(tf.random_normal([n_input]))}


# Building the encoder and decoder
def encoder(x):
    # Encoder first layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']), biases['encoder_b1']))

    # Encoder second layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']), biases['encoder_b2']))

    # Encoder third layer with sigmoid activation #3
    layer_3 = tf.nn.sigmoid(tf.add(tf.matmul(layer_2, weights['encoder_h3']), biases['encoder_b3']))
    return layer_3


def decoder(x):
    # Decoder first layer with sigmoid activation #1
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']), biases['decoder_b1']))

    # Decoder second layer with sigmoid activation #2
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']), biases['decoder_b2']))

    # Decoder second layer with sigmoid activation #3
    layer_3 = tf.nn.sigmoid(tf.add(tf.matmul(layer_2, weights['decoder_h3']), biases['decoder_b3']))
    return layer_3


# In place of variable cost we have loss function and in optimizer we have gradient used for back prop
# Construct model, encoder and decoder operation
encoder_op = encoder(X)
decoder_op = decoder(encoder_op)

# Prediction
y_pred = decoder_op

# Targets (Labels) are the input data.
y_true = X

# 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)

# Initialize the variables
init = tf.global_variables_initializer()

# Launching the graph
sess = tf.Session()
sess.run(init)

# Batch Size
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 5 epoch steps
    if epoch % display_step == 0:
        print("Epoch: ", '%02d' % (epoch + 1), "cost = ", "{:.9f}".format(c))
print("Optimization Finished!")

# Applying encode and decode over test set, Select the number of test cases as well
encode_decode = sess.run(y_pred, feed_dict={X: mnist.test.images[:10]})

# Compare original images with their reconstructions
f, a = plt.subplots(2, 10, figsize=(10, 2))

# Change range function to show the any number of examples to compare from
for i in range(10):
    a[0][i].imshow(np.reshape(mnist.test.images[i], (28, 28)), cmap='gray')
    a[1][i].imshow(np.reshape(encode_decode[i], (28, 28)), cmap='gray')
plt.show()