#!/usr/bin/env python
# coding: utf-8

# # Multilayer Perceptron in TensorFlow
# 
# Credits: Forked from [TensorFlow-Examples](https://github.com/aymericdamien/TensorFlow-Examples) by Aymeric Damien
# 
# ## Setup
# 
# Refer to the [setup instructions](http://nbviewer.ipython.org/github/donnemartin/data-science-ipython-notebooks/blob/master/deep-learning/tensor-flow-examples/Setup_TensorFlow.md)

# In[2]:


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


# In[3]:


import tensorflow as tf


# In[4]:


# Parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
display_step = 1


# In[5]:


# Network Parameters
n_hidden_1 = 256 # 1st layer num features
n_hidden_2 = 256 # 2nd layer num features
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)


# In[6]:


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


# In[7]:


# Create model
def multilayer_perceptron(_X, _weights, _biases):
    #Hidden layer with RELU activation
    layer_1 = tf.nn.relu(tf.add(tf.matmul(_X, _weights['h1']), _biases['b1'])) 
    #Hidden layer with RELU activation
    layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1, _weights['h2']), _biases['b2'])) 
    return tf.matmul(layer_2, weights['out']) + biases['out']


# In[8]:


# Store layers weight & bias
weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}


# In[9]:


# Construct model
pred = multilayer_perceptron(x, weights, biases)


# In[10]:


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


# In[11]:


# Initializing the variables
init = tf.global_variables_initializer()


# In[12]:


# Launch the graph
with tf.Session() as sess:
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # 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
            sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys})
            # Compute average loss
            avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys})/total_batch
        # Display logs per epoch step
        if epoch % display_step == 0:
            print "Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost)

    print "Optimization Finished!"

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    print "Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels})