In [3]:

    

from tensorflow.examples.tutorials.mnist import input_data


    

In [5]:

    

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
import tensorflow as tf
x = tf.placeholder("float", shape = [None, 784])
y_ = tf.placeholder("float", shape = [None, 10])

x_image = tf.reshape(x, [-1, 28, 28, 1])


    

    




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 [6]:

    

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)


    

In [7]:

    

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)


    

In [8]:

    

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')


    

In [9]:

    

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')


    

In [10]:

    

W_conv1 = weight_variable([5, 1, 1, 32])
b_conv1 = bias_variable([32])


    

In [11]:

    

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)


    

In [12]:

    

W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)


    

In [14]:

    

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])


    

In [15]:

    

h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1)+ b_fc1)


    

In [16]:

    

keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)


    

In [17]:

    

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)


    

In [22]:

    

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(200):
    batch = mnist.train.next_batch(50)
    if i%10 == 0:
        train_accuracy = sess.run(accuracy, feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
        print("step %d, training accuracy %g" % (i, train_accuracy))
    sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
    
print("test accuracy %g" % sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))


    

    




step 0, training accuracy 0.08
step 10, training accuracy 0.1
step 20, training accuracy 0.34
step 30, training accuracy 0.26
step 40, training accuracy 0.44
step 50, training accuracy 0.72
step 60, training accuracy 0.6
step 70, training accuracy 0.74
step 80, training accuracy 0.68
step 90, training accuracy 0.74
step 100, training accuracy 0.84
step 110, training accuracy 0.68
step 120, training accuracy 0.8
step 130, training accuracy 0.88
step 140, training accuracy 0.88
step 150, training accuracy 0.84
step 160, training accuracy 0.84
step 170, training accuracy 0.82
step 180, training accuracy 0.94
step 190, training accuracy 0.84
test accuracy 0.889

In [ ]: