1.数据集
CIFAR_10
192.168.9.5：/DATACENTER1/zhiwen.wang/tensorflow-wzw/tensorflow_learn/CIFAR_10/cifar-10-batches
2.代码
192.168.9.5：/DATACENTER1/zhiwen.wang/tensorflow-wzw/tensorflow_learn/CIFAR_10/cifar10
wzwtrain13.py
# -*- coding: utf-8 -*-
"""
Created on 2019
@author: wzw
"""
'''
建立一个带有全局平均池化层的卷积神经网络 并对CIFAR-10数据集进行分类
1.使用3个卷积层的同卷积操作，滤波器大小为5x5，每个卷积层后面都会跟一个步长为2x2的池化层，滤波器大小为2x2
2.对输出的10个feature map进行全局平均池化，得到10个特征
3.对得到的10个特征进行softmax计算，得到分类
'''
import cifar10_input
import tensorflow as tf
import numpy as np
'''
一 引入数据集
'''
batch_size = 256
learning_rate = 1e-4
training_step = 100000
display_step = 200
#数据集目录
data_dir = './cifar-10-batches/cifar-10-batches-bin'
print('begin')
#获取训练集数据
images_train,labels_train = cifar10_input.inputs(eval_data=False,data_dir = data_dir,batch_size=batch_size)
print('begin data')
'''
二 定义网络结构
'''
def weight_variable(shape):
'''
初始化权重
args:
shape：权重shape
'''
initial = tf.truncated_normal(shape=shape,mean=0.0,stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
'''
初始化偏置
args:
shape:偏置shape
'''
initial =tf.constant(0.1,shape=shape)
return tf.Variable(initial)
def conv2d(x,W):
'''
卷积运算 ，使用SAME填充方式 池化层后
out_height = in_hight / strides_height（向上取整）
out_width = in_width / strides_width（向上取整）
args:
x:输入图像 形状为[batch,in_height,in_width,in_channels]
W:权重 形状为[filter_height,filter_width,in_channels,out_channels]
'''
return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool_2x2(x):
'''
最大池化层,滤波器大小为2x2,'SAME'填充方式 池化层后
out_height = in_hight / strides_height（向上取整）
out_width = in_width / strides_width（向上取整）
args:
x:输入图像 形状为[batch,in_height,in_width,in_channels]
'''
return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
def avg_pool_6x6(x):
'''
全局平均池化层，使用一个与原有输入同样尺寸的filter进行池化，'SAME'填充方式 池化层后
out_height = in_hight / strides_height（向上取整）
out_width = in_width / strides_width（向上取整）
args；
x:输入图像 形状为[batch,in_height,in_width,in_channels]
'''
return tf.nn.avg_pool(x,ksize=[1,6,6,1],strides=[1,6,6,1],padding='SAME')
def print_op_shape(t):
'''
输出一个操作op节点的形状
'''
print(t.op.name,'',t.get_shape().as_list())
#定义占位符
input_x = tf.placeholder(dtype=tf.float32,shape=[None,24,24,3]) #图像大小24x24x
input_y = tf.placeholder(dtype=tf.float32,shape=[None,10]) #0-9类别
x_image = tf.reshape(input_x,[-1,24,24,3])
#1.卷积层 ->池化层
W_conv1 = weight_variable([5,5,3,64])
b_conv1 = bias_variable([64])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1) #输出为[-1,24,24,64]
print_op_shape(h_conv1)
h_pool1 = max_pool_2x2(h_conv1) #输出为[-1,12,12,64]
print_op_shape(h_pool1)
#2.卷积层 ->池化层
W_conv2 = weight_variable([5,5,64,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2) #输出为[-1,12,12,64]
print_op_shape(h_conv2)
h_pool2 = max_pool_2x2(h_conv2) #输出为[-1,6,6,64]
print_op_shape(h_pool2)
#3.卷积层 ->全局平均池化层
W_conv3 = weight_variable([5,5,64,10])
b_conv3 = bias_variable([10])
h_conv3 = tf.nn.relu(conv2d(h_pool2,W_conv3) + b_conv3) #输出为[-1,6,6,10]
print_op_shape(h_conv3)
nt_hpool3 = avg_pool_6x6(h_conv3) #输出为[-1,1,1,10]
print_op_shape(nt_hpool3)
nt_hpool3_flat = tf.reshape(nt_hpool3,[-1,10])
y_conv = tf.nn.softmax(nt_hpool3_flat)
'''
三 定义求解器
'''
#softmax交叉熵代价函数
cost = tf.reduce_mean(-tf.reduce_sum(input_y * tf.log(y_conv),axis=1))
#求解器
train = tf.train.AdamOptimizer(learning_rate).minimize(cost)
#返回一个准确度的数据
correct_prediction = tf.equal(tf.arg_max(y_conv,1),tf.arg_max(input_y,1))
#准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,dtype=tf.float32))
'''
四 开始训练
'''
sess = tf.Session();
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)
for step in range(training_step):
with tf.device('/cpu:0'):
image_batch,label_batch = sess.run([images_train,labels_train])
label_b = np.eye(10,dtype=np.float32)[label_batch]
with tf.device('/gpu:0'):
train.run(feed_dict={input_x:image_batch,input_y:label_b},session=sess)
if step % display_step == 0:
train_accuracy = accuracy.eval(feed_dict={input_x:image_batch,input_y:label_b},session=sess)
print('Step {0} tranining accuracy {1}'.format(step,train_accuracy))
3.运行
CUDA_VISIBLE_DEVICES=1 python wzwtrain13.py
4.运行结果