tensorflow60 《TensorFlow技术解析与实战》09 Tensorflow在mnist中的应用

01 softmax

# 《TensorFlow技术解析与实战》09 Tensorflow在mnist中的应用
# win10 Tensorflow-gpu1.2.0 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:nntf09.01.py mnist_softmax.py
# https://github.com/tensorflow/tensorflow/blob/v1.2.0/tensorflow/examples/tutorials/mnist/mnist_softmax.py

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================


"""A very simple MNIST classifier. 

See extensive documentation at 
https://www.tensorflow.org/get_started/mnist/beginners 
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import sys

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

FLAGS = None


def main(_):
    # Import data
    mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)

    # Create the model
    x = tf.placeholder(tf.float32, [None, 784])
    W = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))
    y = tf.matmul(x, W) + b

    # Define loss and optimizer
    y_ = tf.placeholder(tf.float32, [None, 10])

    # The raw formulation of cross-entropy,
    #
    #   tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
    #                                 reduction_indices=[1]))
    #
    # can be numerically unstable.
    #
    # So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
    # outputs of 'y', and then average across the batch.
    cross_entropy = tf.reduce_mean(
        tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
    train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

    sess = tf.InteractiveSession()
    tf.global_variables_initializer().run()
    # Train
    for _ in range(1000):
        batch_xs, batch_ys = mnist.train.next_batch(100)
        sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})


        # Test trained model
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print(sess.run(accuracy, feed_dict={x: mnist.test.images,
                                        y_: mnist.test.labels}))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
                        help='Directory for storing input data')
    FLAGS, unparsed = parser.parse_known_args()
    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
'''
0.9184
'''

02 训练过程可视化

# 《TensorFlow技术解析与实战》09 Tensorflow在mnist中的应用
# win10 Tensorflow-gpu1.2.0 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:nntf09.02.py 训练过程可视化
# https://github.com/tensorflow/tensorflow/blob/v1.2.0/tensorflow/examples/tutorials/mnist/mnist_with_summaries.py

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the 'License');
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an 'AS IS' BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""A simple MNIST classifier which displays summaries in TensorBoard. 

This is an unimpressive MNIST model, but it is a good example of using 
tf.name_scope to make a graph legible in the TensorBoard graph explorer, and of 
naming summary tags so that they are grouped meaningfully in TensorBoard. 

It demonstrates the functionality of every TensorBoard dashboard. 
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import sys

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

FLAGS = None


def train():
    # Import data
    mnist = input_data.read_data_sets(FLAGS.data_dir,
                                      one_hot=True,
                                      fake_data=FLAGS.fake_data)

    sess = tf.InteractiveSession()
    # Create a multilayer model.


    # Input placeholders
    with tf.name_scope('input'):
        x = tf.placeholder(tf.float32, [None, 784], name='x-input')
        y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')

    with tf.name_scope('input_reshape'):
        image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
        tf.summary.image('input', image_shaped_input, 10)


        # We can't initialize these variables to 0 - the network will get stuck.

    def weight_variable(shape):
        """Create a weight variable with appropriate initialization."""
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)

    def bias_variable(shape):
        """Create a bias variable with appropriate initialization."""
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)

    def variable_summaries(var):
        """Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
        with tf.name_scope('summaries'):
            mean = tf.reduce_mean(var)
            tf.summary.scalar('mean', mean)
            with tf.name_scope('stddev'):
                stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
            tf.summary.scalar('stddev', stddev)
            tf.summary.scalar('max', tf.reduce_max(var))
            tf.summary.scalar('min', tf.reduce_min(var))
            tf.summary.histogram('histogram', var)

    def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
        """Reusable code for making a simple neural net layer. 

        It does a matrix multiply, bias add, and then uses ReLU to nonlinearize. 
        It also sets up name scoping so that the resultant graph is easy to read, 
        and adds a number of summary ops.  
        """
        # Adding a name scope ensures logical grouping of the layers in the graph.
        with tf.name_scope(layer_name):
            # This Variable will hold the state of the weights for the layer
            with tf.name_scope('weights'):
                weights = weight_variable([input_dim, output_dim])
                variable_summaries(weights)
            with tf.name_scope('biases'):
                biases = bias_variable([output_dim])
                variable_summaries(biases)
            with tf.name_scope('Wx_plus_b'):
                preactivate = tf.matmul(input_tensor, weights) + biases
                tf.summary.histogram('pre_activations', preactivate)
            activations = act(preactivate, name='activation')
            tf.summary.histogram('activations', activations)
            return activations

    hidden1 = nn_layer(x, 784, 500, 'layer1')

    with tf.name_scope('dropout'):
        keep_prob = tf.placeholder(tf.float32)
        tf.summary.scalar('dropout_keep_probability', keep_prob)
        dropped = tf.nn.dropout(hidden1, keep_prob)


        # Do not apply softmax activation yet, see below.
    y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

    with tf.name_scope('cross_entropy'):
        # The raw formulation of cross-entropy,
        #
        # tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.softmax(y)),
        #                               reduction_indices=[1]))
        #
        # can be numerically unstable.
        #
        # So here we use tf.nn.softmax_cross_entropy_with_logits on the
        # raw outputs of the nn_layer above, and then average across
        # the batch.
        diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)
        with tf.name_scope('total'):
            cross_entropy = tf.reduce_mean(diff)
    tf.summary.scalar('cross_entropy', cross_entropy)

    with tf.name_scope('train'):
        train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
            cross_entropy)

    with tf.name_scope('accuracy'):
        with tf.name_scope('correct_prediction'):
            correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        with tf.name_scope('accuracy'):
            accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    tf.summary.scalar('accuracy', accuracy)

    # Merge all the summaries and write them out to
    # /tmp/tensorflow/mnist/logs/mnist_with_summaries (by default)
    merged = tf.summary.merge_all()
    train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
    test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
    tf.global_variables_initializer().run()

    # Train the model, and also write summaries.
    # Every 10th step, measure test-set accuracy, and write test summaries
    # All other steps, run train_step on training data, & add training summaries


    def feed_dict(train):
        """Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
        if train or FLAGS.fake_data:
            xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
            k = FLAGS.dropout
        else:
            xs, ys = mnist.test.images, mnist.test.labels
            k = 1.0
        return {x: xs, y_: ys, keep_prob: k}

    for i in range(FLAGS.max_steps):
        if i % 10 == 0:  # Record summaries and test-set accuracy
            summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
            test_writer.add_summary(summary, i)
            print('Accuracy at step %s: %s' % (i, acc))
        else:  # Record train set summaries, and train
            if i % 100 == 99:  # Record execution stats
                run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
                run_metadata = tf.RunMetadata()
                summary, _ = sess.run([merged, train_step],
                                      feed_dict=feed_dict(True),
                                      options=run_options,
                                      run_metadata=run_metadata)
                train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
                train_writer.add_summary(summary, i)
                print('Adding run metadata for', i)
            else:  # Record a summary
                summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
                train_writer.add_summary(summary, i)
    train_writer.close()
    test_writer.close()


def main(_):
    if tf.gfile.Exists(FLAGS.log_dir):
        tf.gfile.DeleteRecursively(FLAGS.log_dir)
    tf.gfile.MakeDirs(FLAGS.log_dir)
    train()


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--fake_data', nargs='?', const=True, type=bool,
                        default=False,
                        help='If true, uses fake data for unit testing.')
    parser.add_argument('--max_steps', type=int, default=1000,
                        help='Number of steps to run trainer.')
    parser.add_argument('--learning_rate', type=float, default=0.001,
                        help='Initial learning rate')
    parser.add_argument('--dropout', type=float, default=0.9,
                        help='Keep probability for training dropout.')
    parser.add_argument(
        '--data_dir',
        type=str,
        default='/tmp/tensorflow/mnist/input_data',
        help='Directory for storing input data')
    parser.add_argument(
        '--log_dir',
        type=str,
        default='/tmp/tensorflow/mnist/logs/mnist_with_summaries',
        help='Summaries log directory')
    FLAGS, unparsed = parser.parse_known_args()
    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
'''
Accuracy at step 0: 0.043
Accuracy at step 10: 0.7122
Accuracy at step 20: 0.8203
...
Accuracy at step 980: 0.9665
Accuracy at step 990: 0.9664
Adding run metadata for 999
'''

03 卷积神经网络

# 《TensorFlow技术解析与实战》09 Tensorflow在mnist中的应用
# win10 Tensorflow-gpu1.2.0 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:nntf09.03.py 卷积神经网络
# https://github.com/nlintz/TensorFlow-Tutorials/blob/master/05_convolutional_net.py

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

batch_size = 128
test_size = 256

def init_weights(shape):
    return tf.Variable(tf.random_normal(shape, stddev=0.01))

def model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden):
    l1a = tf.nn.relu(tf.nn.conv2d(X, w,  # l1a shape=(?, 28, 28, 32)
                                  strides=[1, 1, 1, 1], padding='SAME'))
    l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1],  # l1 shape=(?, 14, 14, 32)
                        strides=[1, 2, 2, 1], padding='SAME')
    l1 = tf.nn.dropout(l1, p_keep_conv)

    l2a = tf.nn.relu(tf.nn.conv2d(l1, w2,  # l2a shape=(?, 14, 14, 64)
                                  strides=[1, 1, 1, 1], padding='SAME'))
    l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1],  # l2 shape=(?, 7, 7, 64)
                        strides=[1, 2, 2, 1], padding='SAME')
    l2 = tf.nn.dropout(l2, p_keep_conv)

    l3a = tf.nn.relu(tf.nn.conv2d(l2, w3,  # l3a shape=(?, 7, 7, 128)
                                  strides=[1, 1, 1, 1], padding='SAME'))
    l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1],  # l3 shape=(?, 4, 4, 128)
                        strides=[1, 2, 2, 1], padding='SAME')
    l3 = tf.reshape(l3, [-1, w4.get_shape().as_list()[0]])  # reshape to (?, 2048)
    l3 = tf.nn.dropout(l3, p_keep_conv)

    l4 = tf.nn.relu(tf.matmul(l3, w4))
    l4 = tf.nn.dropout(l4, p_keep_hidden)

    pyx = tf.matmul(l4, w_o)
    return pyx


mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
trX = trX.reshape(-1, 28, 28, 1)  # 28x28x1 input img
teX = teX.reshape(-1, 28, 28, 1)  # 28x28x1 input img

X = tf.placeholder("float", [None, 28, 28, 1])
Y = tf.placeholder("float", [None, 10])

w = init_weights([3, 3, 1, 32])  # 3x3x1 conv, 32 outputs
w2 = init_weights([3, 3, 32, 64])  # 3x3x32 conv, 64 outputs
w3 = init_weights([3, 3, 64, 128])  # 3x3x32 conv, 128 outputs
w4 = init_weights([128 * 4 * 4, 625])  # FC 128 * 4 * 4 inputs, 625 outputs
w_o = init_weights([625, 10])  # FC 625 inputs, 10 outputs (labels)

p_keep_conv = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)

# Launch the graph in a session
with tf.Session() as sess:
    # you need to initialize all variables
    tf.global_variables_initializer().run()

    for i in range(100):
        training_batch = zip(range(0, len(trX), batch_size),
                             range(batch_size, len(trX) + 1, batch_size))
        for start, end in training_batch:
            sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end],
                                          p_keep_conv: 0.8, p_keep_hidden: 0.5})

        test_indices = np.arange(len(teX))  # Get A Test Batch
        np.random.shuffle(test_indices)
        test_indices = test_indices[0:test_size]

        print(i, np.mean(np.argmax(teY[test_indices], axis=1) ==
                         sess.run(predict_op, feed_dict={X: teX[test_indices],
                                                         p_keep_conv: 1.0,
                                                         p_keep_hidden: 1.0})))
'''
0 0.93359375
1 0.97265625
2 0.984375
...
97 0.98828125
98 0.9921875
99 0.99609375
'''

04 循环神经网络

# 《TensorFlow技术解析与实战》09 Tensorflow在mnist中的应用
# win10 Tensorflow-gpu1.2.0 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:nntf09.04.py 循环神经网络
# https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py

''' 
A Recurrent Neural Network (LSTM) implementation example using TensorFlow library. 
This example is using the MNIST database of handwritten digits (http://yann.lecun.com/exdb/mnist/) 
Long Short Term Memory paper: http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf 

Author: Aymeric Damien 
Project: https://github.com/aymericdamien/TensorFlow-Examples/ 
'''

from __future__ import print_function
import tensorflow as tf
from tensorflow.contrib import rnn

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

''' 
To classify images using a recurrent neural network, we consider every image 
row as a sequence of pixels. Because MNIST image shape is 28*28px, we will then 
handle 28 sequences of 28 steps for every sample. 
'''

# Parameters
learning_rate = 0.001
training_iters = 100000
batch_size = 128
display_step = 10

# Network Parameters
n_input = 28  # MNIST data input (img shape: 28*28)
n_steps = 28  # timesteps
n_hidden = 128  # hidden layer num of features
n_classes = 10  # MNIST total classes (0-9 digits)

# tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])

# Define weights
weights = {
    'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}
biases = {
    'out': tf.Variable(tf.random_normal([n_classes]))
}


def RNN(x, weights, biases):
    # Prepare data shape to match `rnn` function requirements
    # Current data input shape: (batch_size, n_steps, n_input)
    # Required shape: 'n_steps' tensors list of shape (batch_size, n_input)

    # Unstack to get a list of 'n_steps' tensors of shape (batch_size, n_input)
    x = tf.unstack(x, n_steps, 1)

    # Define a lstm cell with tensorflow
    lstm_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)

    # Get lstm cell output
    outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32)

    # Linear activation, using rnn inner loop last output
    return tf.matmul(outputs[-1], weights['out']) + biases['out']


pred = RNN(x, weights, biases)

# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initializing the variables
init = tf.global_variables_initializer()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    step = 1
    # Keep training until reach max iterations
    while step * batch_size < training_iters:
        batch_x, batch_y = mnist.train.next_batch(batch_size)
        # Reshape data to get 28 seq of 28 elements
        batch_x = batch_x.reshape((batch_size, n_steps, n_input))
        # Run optimization op (backprop)
        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
        if step % display_step == 0:
            # Calculate batch accuracy
            acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
            # Calculate batch loss
            loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
            print("Iter " + str(step * batch_size) + ", Minibatch Loss= " + \
                  "{:.6f}".format(loss) + ", Training Accuracy= " + \
                  "{:.5f}".format(acc))
        step += 1
    print("Optimization Finished!")

    # Calculate accuracy for 128 mnist test images
    test_len = 128
    test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input))
    test_label = mnist.test.labels[:test_len]
    print("Testing Accuracy:", \
          sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
'''
Iter 1280, Minibatch Loss= 1.832278, Training Accuracy= 0.35156
Iter 2560, Minibatch Loss= 1.582875, Training Accuracy= 0.46875
...
Iter 96000, Minibatch Loss= 0.072946, Training Accuracy= 0.98438
Iter 97280, Minibatch Loss= 0.086200, Training Accuracy= 0.96875
Iter 98560, Minibatch Loss= 0.158176, Training Accuracy= 0.95312
Iter 99840, Minibatch Loss= 0.084359, Training Accuracy= 0.96875
Optimization Finished!
Testing Accuracy: 0.976563
'''

05 TensorFlow自编码网络

# 《TensorFlow技术解析与实战》09 Tensorflow在mnist中的应用
# win10 Tensorflow-gpu1.2.0 python3.5.3
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# filename:nntf09.05.py TensorFlow自编码网络
# https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/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 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 = 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)

# 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.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()
'''
Epoch: 0001 cost= 0.228296980
Epoch: 0002 cost= 0.194890261
Epoch: 0003 cost= 0.180403829
...
Epoch: 0018 cost= 0.137072384
Epoch: 0019 cost= 0.134065136
Epoch: 0020 cost= 0.130218327
Optimization Finished!
'''