#encoding=utf-8 
import tensorflow as tf  
import numpy as np  
from tensorflow.examples.tutorials.mnist import input_data  
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)  
def weight_variable(shape): 
  initial = tf.truncated_normal(shape,stddev=0.1) #截?cái)嗾龖B(tài)分布，此函數(shù)原型為尺寸、均值、標(biāo)準(zhǔn)差 
  return tf.Variable(initial) 
def bias_variable(shape): 
  initial = tf.constant(0.1,shape=shape) 
  return tf.Variable(initial) 
def conv2d(x,W): 
  return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME') # strides第0位和第3為一定為1，剩下的是卷積的橫向和縱向步長(zhǎng) 
def max_pool_2x2(x): 
  return tf.nn.max_pool(x,ksize = [1,2,2,1],strides=[1,2,2,1],padding='SAME')# 參數(shù)同上，ksize是池化塊的大小 
 
x = tf.placeholder("float", shape=[None, 784]) 
y_ = tf.placeholder("float", shape=[None, 10]) 
 
# 圖像轉(zhuǎn)化為一個(gè)四維張量，第一個(gè)參數(shù)代表樣本數(shù)量，-1表示不定，第二三參數(shù)代表圖像尺寸，最后一個(gè)參數(shù)代表圖像通道數(shù) 
x_image = tf.reshape(x,[-1,28,28,1]) 
 
# 第一層卷積加池化 
w_conv1 = weight_variable([5,5,1,32]) # 第一二參數(shù)值得卷積核尺寸大小，即patch，第三個(gè)參數(shù)是圖像通道數(shù)，第四個(gè)參數(shù)是卷積核的數(shù)目，代表會(huì)出現(xiàn)多少個(gè)卷積特征 
b_conv1 = bias_variable([32]) 
 
h_conv1 = tf.nn.relu(conv2d(x_image,w_conv1)+b_conv1) 
h_pool1 = max_pool_2x2(h_conv1) 
 
# 第二層卷積加池化  
w_conv2 = weight_variable([5,5,32,64]) # 多通道卷積，卷積出64個(gè)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) 
 
# 原圖像尺寸28*28，第一輪圖像縮小為14*14，共有32張，第二輪后圖像縮小為7*7，共有64張 
 
w_fc1 = weight_variable([7*7*64,1024]) 
b_fc1 = bias_variable([1024]) 
 
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64]) # 展開，第一個(gè)參數(shù)為樣本數(shù)量，-1未知 
f_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,w_fc1)+b_fc1) 
 
# dropout操作，減少過擬合 
keep_prob = tf.placeholder(tf.float32) 
h_fc1_drop = tf.nn.dropout(f_fc1,keep_prob) 
 
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_sum(y_*tf.log(y_conv)) # 定義交叉熵為loss函數(shù) 
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) # 調(diào)用優(yōu)化器優(yōu)化 
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1)) 
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) 
 
sess = tf.InteractiveSession() 
sess.run(tf.initialize_all_variables()) 
for i in range(2000): 
 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[0:500], y_: mnist.test.labels[0:500], keep_prob: 1.0})