【tensorflow】Cifar10卷积神经网络实时训练过程

【tensorflow】Cifar10卷积神经网络实时训练过程

执行环境，可能出现
AttributeError: module 'tensorflow.python.ops.image_ops' has no attribute 'per_image_whitening'
需要将cifar10_input.py 的182行改为per_image_whitening 改为 per_image_standardization

cifar10_input.py 和cifar10.py 下载地址

#coding=utf-8
import cifar10,cifar10_input
from matplotlib import pyplot as plt
import tensorflow as tf
import numpy as np
import time
import mathmax_steps = 4500
batch_size = 128data_dir = './cifar10_data/cifar-10-batches-bin'
#下载好的数据集所在的文件夹def variable_with_weight_loss(shape, stddev, wl):var = tf.uncated_normal(shape, stddev=stddev))if wl is not None:weight_loss = tf.l2_loss(var), wl, name='weight_loss')## wl 控制l2损失的比重tf.add_to_collection('losses', weight_loss) ## 参数的l2损失加入到损失集合中return vardef loss(logits, labels):labels = tf.cast(labels, tf.int64)cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name='cross_entropy_per_example')# logits为[batch_size，num_classes]# labels为[batch_size，]的一维向量，其中每一个元素代表对应样本的类别# 先对网络的输出 Logits 进行 Softmax 概率化# Cross-Entropy 每个样本的交叉熵（损失）cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')# 一个 batch 内样本求平均损失tf.add_to_collection('losses', cross_entropy_mean)return tf.add__collection('losses'), name='total_loss') # get 损失集合中所有损失，并相加后返回损失总和# cifar10.maybe_download_and_extract()
# 如果没有下载，则需要将该行注释取消，
# 当然检查到 data_dir 目录下已经下载好的，则自动取消下载images_train, labels_train = cifar10_input.distorted_inputs(data_dir=data_dir,batch_size=batch_size)images_test, labels_test = cifar10_input.inputs(eval_data=True,data_dir=data_dir,batch_size=batch_size)                                                  
#images_train, labels_train = cifar10.distorted_inputs()
#images_test, labels_test = cifar10.inputs(eval_data=True)image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])
label_holder = tf.placeholder(tf.int32, [batch_size])
#原始图像是32*32*3，distorted_inputs函数随机裁剪，旋转成24*24*3的尺寸
#inputs用于测试集，只在正中间裁剪成24*24*3的尺寸
#logits = inference(image_holder)#############################第一层卷积层###################################
weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64], stddev=5e-2, wl=0.0)
kernel1 = v2d(image_holder, weight1, [1, 1, 1, 1], padding='SAME')
bias1 = tf.stant(0.0, shape=[64]))
conv1 = tf.nn