测试Minist 数据集

#!/usr/bin/python
import tensorflow as tf
import sys
from tensorflow.examples.tutorials.mnist import input_data
#定义一个函数，用于初始化所有的权值 W
def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)
#定义一个函数，用于初始化所有的偏置项 b
def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)
#定义一个函数，用于构建卷积层
def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#定义一个函数，用于构建池化层
def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

#下载并加载数据
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)


#数据与标签的占位
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])

W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

#构建网络
x_image = tf.reshape(x, [-1, 28, 28, 1])  #转换输入数据shape,以便于用于网络中

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)    #第一个卷积层
h_pool1 = max_pool_2x2(h_conv1)                             #第一个池化层
#初始化权重和偏置
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)    #第二个卷积层
h_pool2 = max_pool_2x2(h_conv2)                             #第二个池化层

# Now image size is reduced to 7*7
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])            #reshape成向量
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)  #第一个全连接层

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

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
#softmax回归，得到预测概率
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)  #softmax层

#求交叉熵得到残差
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))           #交叉熵

train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)    #梯度下降法
#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"))                 #精确度计算

# tf.session()
sess = tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    #训练，迭代1000次
    for i in range(10000):
      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 %.3f"%(i, train_accuracy))
        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

        print ("Training finished")

        print( "test accuracy %.3f" % accuracy.eval(feed_dict={
            x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))