Introduction to TensorFlow

In [1]:

    

import tensorflow as tf


    

In [2]:

    

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)


    

    




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

In [3]:

    

X = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))


    

In [4]:

    

# model
Y = tf.nn.softmax(tf.matmul(X, W) + b)


    

In [5]:

    

# placeholder for correct answers ("one-hot" encoded)
Y_ = tf.placeholder(tf.float32, [None, 10])


    

In [6]:

    

# loss function
cross_entropy = tf.reduce_mean(-tf.reduce_sum(Y_ * tf.log(Y), reduction_indices=[1]))


    

In [7]:

    

# % of correct answers found in batch
is_correct = tf.equal(tf.argmax(Y,1), tf.argmax(Y_,1))
accuracy = tf.reduce_mean(tf.cast(is_correct, tf.float32))


    

In [8]:

    

# traning
optimizer = tf.train.GradientDescentOptimizer(0.003) # learning rate
train_step = optimizer.minimize(cross_entropy)  # loss function


    

In [9]:

    

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)


    

In [10]:

    

for i in range(1000):
    # load batch of images and correct answers
    batch_X, batch_Y = mnist.train.next_batch(100)
    train_data = {X: batch_X, Y_: batch_Y}
    
    # train
    sess.run(train_step, feed_dict=train_data)
        
    # success on test data ?
    test_data = {X: mnist.test.images, Y_: mnist.test.labels}
    a, c = sess.run([accuracy, cross_entropy], feed_dict=test_data)


    

In [ ]: