In [3]:

    

import tensorflow as tf


    

In [7]:

    

sess = tf.InteractiveSession()


    

In [8]:

    

x  = tf.placeholder(tf.float32,shape=[None,784])
y_ = tf.placeholder(tf.float32,shape=[None,10])


    

In [9]:

    

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


    

In [10]:

    

sess.run(tf.initialize_all_variables())


    

In [11]:

    

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


    

In [12]:

    

cross_entropy = -tf.reduce_sum(y_*tf.log(y))


    

In [13]:

    

Opt = tf.train.GradientDescentOptimizer(0.01)


    

In [15]:

    

train_step = Opt.minimize(cross_entropy)


    

In [16]:

    

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


    

In [17]:

    

def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding="SAME")
def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding="SAME")


    

In [19]:

    

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


    

In [20]:

    

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


    

In [23]:

    

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


    

In [25]:

    

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 [26]:

    

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


    

In [27]:

    

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 [28]:

    

keep_prob = tf.placeholder(tf.float32)


    

In [29]:

    

h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)


    

In [30]:

    

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 [31]:

    

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.GradientDescentOptimizer(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,tf.float32))
sess.run(tf.initialize_all_variables())
for i in xrange(20000):
    batch = minist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
        print("step %d, trainning accuracy %g" %(i,train_accuracy))
    train_step.run(feed_dict={x:batch[0],y:batch[1],keep_prob:0.5})
print("test accuracy %g" % accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-31-c5caa264f3c7> in <module>()
      5 sess.run(tf.initialize_all_variables())
      6 for i in xrange(20000):
----> 7     batch = minist.train.next_batch(50)
      8     if i%100 == 0:
      9         train_accuracy = accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})

NameError: name 'minist' is not defined

In [ ]: