

In [2]:

    
# -*- 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 MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_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 = 500 # 1st layer num features
n_hidden_2 = 500 # 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)

# Prediction
y_pred = decoder_op
# Targets (Labels) are the input data.
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.global_variables_initializer()

# Launch the graph
# with tf.Session() as sess:
sess = tf.Session()
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)
        # 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:", '%04d' % (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)))
f.show()
plt.draw()
    # plt.waitforbuttonpress()









    



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
Epoch: 0001 cost= 0.204699397
Epoch: 0002 cost= 0.170914590
Epoch: 0003 cost= 0.162149802
Epoch: 0004 cost= 0.153807685
Epoch: 0005 cost= 0.151990861
Epoch: 0006 cost= 0.143229485
Epoch: 0007 cost= 0.140273750
Epoch: 0008 cost= 0.138306111
Epoch: 0009 cost= 0.134088472
Epoch: 0010 cost= 0.133033127
Epoch: 0011 cost= 0.127716810
Epoch: 0012 cost= 0.130891845
Epoch: 0013 cost= 0.127566263
Epoch: 0014 cost= 0.127612963
Epoch: 0015 cost= 0.124548510
Epoch: 0016 cost= 0.121631041
Epoch: 0017 cost= 0.118263461
Epoch: 0018 cost= 0.118914150
Epoch: 0019 cost= 0.115665138
Epoch: 0020 cost= 0.114136405
Optimization Finished!






    



/opt/conda/lib/python3.5/site-packages/matplotlib/figure.py:397: UserWarning: matplotlib is currently using a non-GUI backend, so cannot show the figure
  "matplotlib is currently using a non-GUI backend, "



In [3]:

    
examples_to_show = 8
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, 5, figsize=(5, 2))


plt.figure(figsize=(8, 2))
for i in range(8):

    ax = plt.subplot(2, 8, i+1)
    plt.imshow(mnist.test.images[i].reshape(28, 28), vmin=0, vmax=1, cmap="gray")
    plt.axis('off')
    ax.set_xticklabels([])
    ax.set_yticklabels([])
    ax.set_aspect('equal')
    
    ax = plt.subplot(2, 8, 8+i+1)
    plt.imshow(encode_decode[i].reshape(28, 28), vmin=0, vmax=1, cmap="gray")
    plt.axis('off')
    ax.set_xticklabels([])
    ax.set_yticklabels([])
    ax.set_aspect('equal')
    
plt.tight_layout()
plt.savefig('../]data/{}.png'.format('ae_pic'), bbox_inches='tight')