Mnist2-CNN

# http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_pros.html
#InteractiveSession -- 能让你在运行图的时候，插入一些计算图, CNN--卷积神经网络
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)

import tensorflow as tf
sess = tf.InteractiveSession()


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

def weight_variable(shape):
    #truncated_normal:截断正态分布，函数产生的随机数与均值的差不会超过两倍的标准差，stddev是标准差
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

# 卷积和池化
def conv2d(x, W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1] , padding='SAME')  #strides--窗口在每一个维度上滑动的步长 ,value--[batch, height, width, channels]--[一个batch的图片数量, 图片高度, 图片宽度, 图像通道数]
                                                                   #filter--[filter_height, filter_width, in_channels, out_channels]--[卷积核的高度，卷积核的宽度，图像通道数，卷积核个数]
def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],                     #ksize--池化窗口的大小
                          strides=[1,2,2,1], padding='SAME')

#convolution1 layer
W_conv1 = weight_variable([5,5,1,32])   #patch大小，输入通道数，输出通道数
b_conv1 = bias_variable([32])
x_image = tf.reshape(x,[-1,28,28,1])    #第2、第3维对应图片的宽、高,第4维维代表图片的颜色通道数,rgb彩色为3
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)  #28*28*32
h_pool1 = max_pool_2x2(h_conv1)         #14*14*32

#convolution2 layer
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)   #14*14*64
h_pool2 = max_pool_2x2(h_conv2)         #7*7*64

#function1 layer  密集连接层
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)   #[-1, 1024]

#dropout:防止过拟合
keep_prob = tf.placeholder("float")   #按照一定的概率将其暂时从网络中丢弃，保持每个元素的概率
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)   #[-1, 1024]

#output 输出层
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)  #[-1,10]

#模型评估
cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
optimization = tf.train.AdamOptimizer(1e-4)
train_step  = optimization.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"))

#初始化变量
init = tf.global_variables_initializer()
sess.run(init)

for i in range(2000):
    batch = mnist.train.next_batch(100)
    train_step.run(feed_dict={x:batch[0], y_:batch[1], keep_prob:0.5})
    # sess.run(train_step,feed_dict={x:batch[0], y_:batch[1], keep_prob:0.5})   #替换也可以
    if i % 100 == 0:      #eval:evaluate
        train_accuracy = accuracy.eval(feed_dict={
             x:batch[0],y_:batch[1],keep_prob:1.0})
        # train_accuracy = sess.run(accuracy,feed_dict={             #替换也可以
        #      x:batch[0],y_:batch[1],keep_prob:1.0})
        print("step %d,train_acc %g" %(i , train_accuracy))     #根据数值的大小，自动选f格式或e格式

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