TensorFlow实现卷积神经网络CNN

#!/usr/bin/env python2 
# -*- coding: utf-8 -*- 
""" 
Created on Thu Mar 9 22:01:46 2017 
 
@author: marsjhao 
""" 
 
import tensorflow as tf 
from tensorflow.examples.tutorials.mnist import input_data 
 
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) #标准差为0.1的正态分布 
 return tf.Variable(initial) 
 
def bias_variable(shape): 
 initial = tf.constant(0.1, shape=shape) #偏差初始化为0.1 
 return tf.Variable(initial) 
 
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') 
 
x = tf.placeholder(tf.float32, [None, 784]) 
y_ = tf.placeholder(tf.float32, [None, 10]) 
# -1代表先不考虑输入的图片例子多少这个维度，1是channel的数量 
x_image = tf.reshape(x, [-1, 28, 28, 1]) 
keep_prob = tf.placeholder(tf.float32) 
 
# 构建卷积层1 
W_conv1 = weight_variable([5, 5, 1, 32]) # 卷积核5*5，1个channel，32个卷积核，形成32个featuremap 
b_conv1 = bias_variable([32]) # 32个featuremap的偏置 
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # 用relu非线性处理 
h_pool1 = max_pool_2x2(h_conv1) # pooling池化 
 
# 构建卷积层2 
W_conv2 = weight_variable([5, 5, 32, 64]) # 注意这里channel值是32 
b_conv2 = bias_variable([64]) 
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) 
h_pool2 = max_pool_2x2(h_conv2) 
 
# 构建全连接层1 
W_fc1 = weight_variable([7*7*64, 1024]) 
b_fc1 = bias_variable([1024]) 
h_pool3 = tf.reshape(h_pool2, [-1, 7*7*64]) 
h_fc1 = tf.nn.relu(tf.matmul(h_pool3, W_fc1) + b_fc1) 
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 
 
# 构建全连接层2 
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) 
 
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.arg_max(y_conv, 1), tf.arg_max(y_, 1)) 
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 
 
tf.global_variables_initializer().run() 
 
for i in range(20001): 
 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}))