In [1]:

    

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
%matplotlib inline
mnist = input_data.read_data_sets('data/', one_hot=True)


    

    




Extracting data/train-images-idx3-ubyte.gz
Extracting data/train-labels-idx1-ubyte.gz
Extracting data/t10k-images-idx3-ubyte.gz
Extracting data/t10k-labels-idx1-ubyte.gz

In [2]:

    

# Use Logistic Regression from our previous example

# Parameters
learning_rate = 0.01
training_epochs = 10
batch_size = 100
display_step = 1

# tf Graph Input
x = tf.placeholder("float", [None, 784], name='x') # mnist data image of shape 28*28=784
y = tf.placeholder("float", [None, 10], name='y') # 0-9 digits recognition => 10 classes

# Create model

# Set model weights
W = tf.Variable(tf.zeros([784, 10]), name="weights")
b = tf.Variable(tf.zeros([10]), name="bias")

# Construct model
activation = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax

# Minimize error using cross entropy
cost = -tf.reduce_sum(y*tf.log(activation)) # Cross entropy
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) # Gradient Descent

# Initializing the variables
init = tf.initialize_all_variables()


    

In [3]:

    

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

    # Set logs writer into folder /tmp/tensorflow_logs
    summary_writer = tf.train.SummaryWriter('/tmp/tensorflow_logs', graph=sess.graph)

    # 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(activation, 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})


    

    




Epoch: 0001 cost= 29.860462506
Epoch: 0002 cost= 22.028559675
Epoch: 0003 cost= 21.019104078
Epoch: 0004 cost= 20.528993900
Epoch: 0005 cost= 20.129545855
Epoch: 0006 cost= 19.980496155
Epoch: 0007 cost= 19.713256450
Epoch: 0008 cost= 19.486078643
Epoch: 0009 cost= 19.291432394
Epoch: 0010 cost= 19.155823388
Optimization Finished!
Accuracy: 0.9236

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: