tensorflow：多层CNN

一般来说，CNN网络的前几层为卷积层和采样层（或者说池化层），在若干层卷积和池化以后，还有若干层全连接层（也就是传统神经网络），最后输出分类信息。大概的结构示意图如下图所示

可以看到，CNN相比与传统神经网络，最大的区别就是引入了卷积层和池化层。这也是我们在代码中要着重看的地方。 
在下面的代码中，卷积是使用tf.nn.conv2d, 池化使用tf.nn.max_pool,下面来详细的讲解一下这两个函数的用法。

---

tf.nn.conv2d

这个函数的功能是：给定4维的input和filter，计算出一个2维的卷积结果。函数的定义为：

def conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None,
           data_format=None, name=None):
 
 
1
2

前几个参数分别是input, filter, strides, padding, use_cudnn_on_gpu, …下面来一一解释 
input：待卷积的数据。格式要求为一个张量，[batch, in_height, in_width, in_channels]. 
分别表示 批次数，图像高度，宽度，输入通道数。 
filter： 卷积核。格式要求为[filter_height, filter_width, in_channels, out_channels]. 
分别表示 卷积核的高度，宽度，输入通道数，输出通道数。 
strides :一个长为4的list. 表示每次卷积以后卷积窗口在input中滑动的距离 
padding ：有SAME和VALID两种选项，表示是否要保留图像边上那一圈不完全卷积的部分。如果是SAME，则保留 
use_cudnn_on_gpu ：是否使用cudnn加速。默认是True

---

tf.nn.max_pool 
进行最大值池化操作,而avg_pool 则进行平均值池化操作.函数的定义为：

def max_pool(value, ksize, strides, padding, data_format="NHWC", name=None):
 
 
1

value: 一个4D张量，格式为[batch, height, width, channels]，与conv2d中input格式一样 
ksize: 长为4的list,表示池化窗口的尺寸 
strides: 池化窗口的滑动值，与conv2d中的一样 

padding: 与conv2d中用法一样。

#coding= "UTF-8"
from __future__ import absolute_import 
from __future__ import division
from __future__ import print_function

#import data
from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf 

flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_string('data_dir','data/',"directory for storing data")

print (FLAGS.data_dir)
mnist = input_data.read_data_sets(FLAGS.data_dir,one_hot = True)


def weight_variable(shape):
	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):
	return tf.nn.max_pool(x,ksize = [1,2,2,1],2
		strides = [1,2,2,1],padding = "SAME")

sess = tf.InteractiveSession()

x = tf.placeholder(tf.float32,[None,784])
x_image = tf.reshape(x,[-1,28,28,1])

#第一层
w_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.elu(conv2d(x_image,w_conv1)+b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#第二层

w_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.elu(conv2d(h_pool1,w_conv2)+b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#第三层
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.elu(tf.matmul(h_pool2_flat,w_fc1)+b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

#第四层
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)
y_ = tf.placeholder(tf.float32,[None,10])

#loss+train
#交叉熵损失函数
loss = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices = [1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)
correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
sess.run(tf.initialize_all_variables())
for i in range(1001):
	batch = mnist.train.next_batch(50)
	if i%100 == 0:
		train_accurancy = sess.run(accuracy,feed_dict = {x:batch[0],y_:batch[1],keep_prob:1.0})
		print('step: %d,training accuracy: %g' % (i,train_accurancy))
	sess.run(train_step,feed_dict = {x:batch[0],y_:batch[1],keep_prob:0.5})

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