Build a 2 layers auto-encoder with TensorFlow to compress images to a lower latent space and then reconstruct them.
References:
This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).
More info: http://yann.lecun.com/exdb/mnist/
In [1]:
from __future__ import division, print_function, absolute_import
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
In [2]:
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
In [3]:
# Training Parameters
learning_rate = 0.01
num_steps = 30000
batch_size = 256
display_step = 1000
examples_to_show = 10
# Network Parameters
num_hidden_1 = 256 # 1st layer num features
num_hidden_2 = 128 # 2nd layer num features (the latent dim)
num_input = 784 # MNIST data input (img shape: 28*28)
# tf Graph input (only pictures)
X = tf.placeholder("float", [None, num_input])
weights = {
'encoder_h1': tf.Variable(tf.random_normal([num_input, num_hidden_1])),
'encoder_h2': tf.Variable(tf.random_normal([num_hidden_1, num_hidden_2])),
'decoder_h1': tf.Variable(tf.random_normal([num_hidden_2, num_hidden_1])),
'decoder_h2': tf.Variable(tf.random_normal([num_hidden_1, num_input])),
}
biases = {
'encoder_b1': tf.Variable(tf.random_normal([num_hidden_1])),
'encoder_b2': tf.Variable(tf.random_normal([num_hidden_2])),
'decoder_b1': tf.Variable(tf.random_normal([num_hidden_1])),
'decoder_b2': tf.Variable(tf.random_normal([num_input])),
}
In [4]:
# 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']))
# Encoder 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):
# Decoder 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
loss = tf.reduce_mean(tf.pow(y_true - y_pred, 2))
optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(loss)
# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()
In [5]:
# Start Training
# Start a new TF session
sess = tf.Session()
# Run the initializer
sess.run(init)
# Training
for i in range(1, num_steps+1):
# Prepare Data
# Get the next batch of MNIST data (only images are needed, not labels)
batch_x, _ = mnist.train.next_batch(batch_size)
# Run optimization op (backprop) and cost op (to get loss value)
_, l = sess.run([optimizer, loss], feed_dict={X: batch_x})
# Display logs per step
if i % display_step == 0 or i == 1:
print('Step %i: Minibatch Loss: %f' % (i, l))
In [6]:
# Testing
# Encode and decode images from test set and visualize their reconstruction.
n = 4
canvas_orig = np.empty((28 * n, 28 * n))
canvas_recon = np.empty((28 * n, 28 * n))
for i in range(n):
# MNIST test set
batch_x, _ = mnist.test.next_batch(n)
# Encode and decode the digit image
g = sess.run(decoder_op, feed_dict={X: batch_x})
# Display original images
for j in range(n):
# Draw the generated digits
canvas_orig[i * 28:(i + 1) * 28, j * 28:(j + 1) * 28] = batch_x[j].reshape([28, 28])
# Display reconstructed images
for j in range(n):
# Draw the generated digits
canvas_recon[i * 28:(i + 1) * 28, j * 28:(j + 1) * 28] = g[j].reshape([28, 28])
print("Original Images")
plt.figure(figsize=(n, n))
plt.imshow(canvas_orig, origin="upper", cmap="gray")
plt.show()
print("Reconstructed Images")
plt.figure(figsize=(n, n))
plt.imshow(canvas_recon, origin="upper", cmap="gray")
plt.show()