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

def weight_variable(shape): 
 initial = tf.truncated_normal(shape, stddev=0.1)
#給權(quán)重制造一些隨機(jī)的噪聲來(lái)打破完全對(duì)稱， 
 return tf.Variable(initial) 
#使用relu，給偏置增加一些小正值0.1，用來(lái)避免死亡節(jié)點(diǎn) 
def bias_variable(shape): 
 initial = tf.constant(0.1, shape=shape) 
 return tf.Variable(initial) 

def conv2d(x,W):#2維卷積函數(shù)，x輸入，w是卷積的參數(shù)，strides代表卷積模板移動(dòng)步長(zhǎng) 
 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') 

x = tf.placeholder(tf.float32, [None, 784])# x 時(shí)特征 
y_ = tf.placeholder(tf.float32, [None, 10])# y_時(shí)真實(shí)的label 
x_image = tf.reshape(x, [-1, 28, 28,1]) 

w_conv1 = weight_variable([5, 5, 1, 32])
#代表卷積核尺寸為5X5，1個(gè)顏色通道，32個(gè)不同的卷積核，使用conv2d函數(shù)進(jìn)行卷積操作， 
b_conv1 = bias_variable([32]) 
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1) 
h_pool1 = max_pool_2x2(h_conv1) 

w_conv2 = weight_variable([5, 5, 32, 64])#這層提取64種特征 
b_conv2 = bias_variable([64]) 
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2) 
h_pool2 = max_pool_2x2(h_conv2) 

w_fc1 = weight_variable([7*7*64, 1024]) 
b_fc1 = bias_variable([1024]) 
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) 

#為了減輕過(guò)擬合，使用一個(gè)Dropout層 
keep_prob = tf.placeholder(tf.float32) 
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 
 
#dropout層的輸出連接一個(gè)softmax層，得到最后的概率輸出 
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) 

#損失函數(shù)，并且定義優(yōu)化器為Adam 
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), 
            reduction_indices=[1])) 
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, tf.float32)) 

#初始化所有參數(shù) 
tf.global_variables_initializer().run() 
for i in range (20000): 
 batch = mnist.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, training 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}))