tensorflow实现cirfar10

# -*- coding: utf-8 -*-
"""
Created on Tue May 23 19:17:27 2017

@author: Administrator
"""

import cifar10,cifar10_input
import tensorflow as tf
import numpy as np 
import time 

max_steps = 3000  #最大训练步数
batch_size = 128  
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'

#权重初始化函数，定义loss，
def variable_with_weight_loss(shape, stddev, w1): 
    var = tf.Variable(tf.truncated_normal(shape, stddev = stddev)) #均匀分布 
    if w1 is not None: 
        weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name = 'weight_loss') #l2正则化乘以loss
        tf.add_to_collection('losses', weight_loss) 
    return var

cifar10.maybe_download_and_extract() #下载并提取数据集，展开至指定位置

images_train,labels_train=cifar10_input.distorted_inputs(data_dir=data_dir,batch_size=batch_size) #产生训练图片和标签数据
images_test, labels_test = cifar10_input.inputs(eval_data = True, data_dir = data_dir, batch_size = batch_size)
#定义placeholder尺寸，图片为24x24,3通道
image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3]) 
label_holder = tf.placeholder(tf.int32, [batch_size])

#第一个卷积层
weight1 = variable_with_weight_loss(shape = [5, 5, 3, 64], stddev = 5e-2, w1 = 0.0) #5x5卷积核，一个64个核，3通道输入
kernel1 = tf.nn.conv2d(image_holder, weight1, [1, 1, 1, 1], padding = 'SAME') #步长1
bias1 = tf.Variable(tf.constant(0.0, shape = [64])) 
conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1))
pool1 = tf.nn.max_pool(conv1, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'SAME') #max_pool窗口3x3,步长2x2
norm1 = tf.nn.lrn(pool1, 4, bias = 1.0, alpha = 0.001 / 9.0, beta = 0.75) #添加lrn处理

#第二个卷积层
weight2 = variable_with_weight_loss(shape = [5, 5, 64, 64], stddev = 5e-2, w1 = 0.0) #5x5卷积核，一个64个核，64输入
kernel2 = tf.nn.conv2d(norm1, weight2, [1, 1, 1, 1], padding = 'SAME') 
bias2 = tf.Variable(tf.constant(0.1, shape = [64])) 
conv2 = tf.nn.relu(tf.nn.bias_add(kernel2, bias2)) 
norm2 = tf.nn.lrn(conv2, 4, bias = 1.0, alpha = 0.001 / 9.0, beta = 0.75) 
pool2 = tf.nn.max_pool(norm2, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'SAME')

#第一个全连接层,384个隐含节点
reshape=tf.reshape(pool2,[batch_size,-1])#全部展开
dim = reshape.get_shape()[1].value 
weight3 = variable_with_weight_loss(shape = [dim, 384], stddev = 0.04, w1 = 0.004) 
bias3 = tf.Variable(tf.constant(0.1, shape = [384])) 
local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3)

#第二全连接层，192个隐含节点
weight4 = variable_with_weight_loss(shape = [384, 192], stddev = 0.04, w1 = 0.004) 
bias4 = tf.Variable(tf.constant(0.1, shape = [192])) 
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4)

#最后一层,输出10
weight5 = variable_with_weight_loss(shape = [192, 10], stddev = 1.0 / 192.0, w1 = 0.0) 
bias5 = tf.Variable(tf.constant(0.0, shape = [10])) 
logits = tf.add(tf.matmul(local4, weight5), bias5)

#定义损失函数，把L2的损失也要加到总的损失中去
def loss(logits, labels): 
    labels = tf.cast(labels, tf.int32) 
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits = logits, labels = labels, name = 'cross_entropy_per_example') 
    cross_entropy_mean = tf.reduce_mean(cross_entropy, name = 'cross_entropy') 
    tf.add_to_collection('losses', cross_entropy_mean) 
    return tf.add_n(tf.get_collection('losses'), name = 'total_loss')

loss=loss(logits,label_holder)
train_op = tf.train.AdamOptimizer(1e-3).minimize(loss) #优化损失函数
#使用tf.nn.in_top_k函数求输出结果中top k 的准确率，默认使用top 1，也就是输出分数最高的那一类的准确率。
top_k_op = tf.nn.in_top_k(logits, label_holder, 1)
#模型初始化
sess = tf.InteractiveSession() 
tf.global_variables_initializer().run()
#启动16个线程
tf.train.start_queue_runners()
#训练步骤
for step in range(max_steps): 
    start_time = time.time() 
    image_batch, label_batch = sess.run([images_train, labels_train])
    _, loss_value = sess.run([train_op, loss], 
       feed_dict = {image_holder: image_batch, label_holder: label_batch}) 
    duration = time.time() - start_time 
    if step % 10 == 0: 
        examples_per_sec = batch_size / duration 
        sec_per_batch = float(duration) 
        format_str = ('step %d, loss = %.2f(%.1f examples/sec; %.3f sec/batch)') 
        print(format_str % (step, loss_value, examples_per_sec, sec_per_batch))

num_examples = 10000 
import math 
num_iter = int(math.ceil(num_examples / batch_size)) 
true_count = 0 
total_sample_count = num_iter * batch_size 
# print total_sample_count 
step = 0 
while step < num_iter: 
    image_batch, label_batch = sess.run([images_test, labels_test]) 
    predictions = sess.run([top_k_op], feed_dict = {image_holder: image_batch, label_holder: label_batch}) 
    true_count += np.sum(predictions) 
    step += 1 
    # print(true_count)

precision = true_count / total_sample_count 
print('precision @ 1 = %.3f' %precision)

结果