In [21]:

    

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 [22]:

    

import tensorflow as tf
x = tf.placeholder(tf.float32, [None, 784])


    

In [23]:

    

W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))


    

In [24]:

    

y = tf.nn.softmax(tf.matmul(x, W) + b)


    

In [25]:

    

y_ = tf.placeholder(tf.float32, [None, 10])


    

In [26]:

    

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))


    

In [55]:

    

train_step = tf.train.GradientDescentOptimizer(0.4).minimize(cross_entropy)


    

In [56]:

    

init = tf.initialize_all_variables()


    

In [57]:

    

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


    

In [58]:

    

for i in range(5000):
  batch_xs, batch_ys = mnist.train.next_batch(200)
  sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})


    

In [59]:

    

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))


    

In [60]:

    

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


    

In [61]:

    

print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))


    

    




0.9227

In [ ]: