tensorflow入门Day4-CNN

# -*- coding: utf-8 -*-
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf 

mnist = input_data.read_data_sets('MNIST_data/',one_hot=True)

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

#-1表示自行推断，1表示只有1个通道
x_image = tf.reshape(x, [-1,28,28,1])

def weight_variable(shape):
	#truncated_normal:截断正态分布随机数，均值mean,标准差stddev,不过只保留[mean-2*stddev,mean+2*stddev]范围内的随机数 
	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)

def conv2d(x,W):
	return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
'''
tf.nn.max_pool(value, ksize, strides, padding, name=None)
第一个参数value：需要池化的输入，一般池化层接在卷积层后面，所以输入通常是feature map，依然是[batch, height, width, channels]这样的shape

第二个参数ksize：池化窗口的大小，取一个四维向量，一般是[1, height, width, 1]，因为我们不想在batch和channels上做池化，所以这两个维度设为了1

第三个参数strides：和卷积类似，窗口在每一个维度上滑动的步长，一般也是[1, stride,stride, 1]

第四个参数padding：和卷积类似，可以取'VALID' 或者'SAME'

返回一个Tensor，类型不变，shape仍然是[batch, height, width, channels]这种形式
'''
	return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

W_conv1 = weight_variable([5, 5, 1, 32]) #1表示1通道
b_conv1 = bias_variable([32])

#卷积层1
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])
b_conv2 = bias_variable([64])

#卷积层2
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])

#全连接层1
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)

#keep_prob用于存储一个神经元被丢掉的概率
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])

#全连接层2
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
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"))

sess = tf.Session()
init = tf.initialize_all_variables()
sess.run(init)

for i in range(1000):
	batch = mnist.train.next_batch(50)
	if i % 10 ==0:
		train_accuracy = sess.run(accuracy, feed_dict={x : batch[0], y_ : batch[1], keep_prob : 1.0})
		print("step %d, training accuracy %g" % (i, train_accuracy))　　
	#%g指数(e)或浮点数 (根据显示长度)
	sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})