In [24]:

    

# Softmax Regression

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


    

In [2]:

    

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


    

    




Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting MNIST_data/train-images-idx3-ubyte.gz
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

In [9]:

    

print(mnist.train.images.shape, mnist.test.images.shape, mnist.validation.images.shape)

print(mnist.train.labels.shape)


    

    




(55000, 784) (10000, 784) (5000, 784)
(55000, 10)

In [11]:

    

sess = tf.InteractiveSession()


    

In [12]:

    

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


    

In [14]:

    

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


    

In [15]:

    

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

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


    

In [16]:

    

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)


    

In [17]:

    

tf.global_variables_initializer().run()


    

In [18]:

    

for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    train_step.run({x:batch_xs, labels:batch_ys})


    

In [33]:

    

correct_pred = tf.equal(tf.argmax(y, 1), tf.argmax(labels, 1))
pred = correct_pred.eval({x:mnist.train.images, labels:mnist.train.labels})

pred = correct_pred.eval({x:mnist.test.images, labels:mnist.test.labels})


    

In [35]:

    

accuracy = np.count_nonzero(pred) / np.size(pred)
print(accuracy)

accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
print(accuracy.eval({x:mnist.test.images, labels:mnist.test.labels}))


    

    




0.9206
0.9206