Tensorflow样例代码分析cifar10
github地址:https://github.com/tensorflow/models.git
本文分析tutorial/image/cifar10教程项目的cifar10_input.py代码。
给外部调用的方法是:
- distorted_inputs()和inputs()
cifar10.py文件调用了此文件中定义的方法。
- """Routine for decoding the CIFAR-10 binary file format."""
- from __future__ import absolute_import
- from __future__ import division
- from __future__ import print_function
- import os
- from six.moves import xrange # pylint: disable=redefined-builtin
- import tensorflow as tf
- # 定义图片的像素,原生图片32 x 32
- # Process images of this size. Note that this differs from the original CIFAR
- # image size of 32 x 32. If one alters this number, then the entire model
- # architecture will change and any model would need to be retrained.
- # IMAGE_SIZE = 24
- IMAGE_SIZE = 32
- # Global constants describing the CIFAR-10 data set.
- # 分类数量
- NUM_CLASSES = 10
- # 训练集大小
- NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 50000
- # 评价集大小
- NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000
- # 从CIFAR10数据文件中读取样例
- # filename_queue一个队列的文件名
- def read_cifar10(filename_queue):
- class CIFAR10Record(object):
- pass
- result = CIFAR10Record()
- # Dimensions of the images in the CIFAR-10 dataset.
- # See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
- # input format.
- # 分类结果的长度,CIFAR-100长度为2
- label_bytes = 1 # 2 for CIFAR-100
- result.height = 32
- result.width = 32
- # 3位表示rgb颜色(0-255,0-255,0-255)
- result.depth = 3
- image_bytes = result.height * result.width * result.depth
- # Every record consists of a label followed by the image, with a
- # fixed number of bytes for each.
- # 单个记录的总长度=分类结果长度+图片长度
- record_bytes = label_bytes + image_bytes
- # Read a record, getting filenames from the filename_queue. No
- # header or footer in the CIFAR-10 format, so we leave header_bytes
- # and footer_bytes at their default of 0.
- # 读取
- reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
- result.key, value = reader.read(filename_queue)
- # Convert from a string to a vector of uint8 that is record_bytes long.
- record_bytes = tf.decode_raw(value, tf.uint8)
- # 第一位代表lable-图片的正确分类结果,从uint8转换为int32类型
- # The first bytes represent the label, which we convert from uint8->int32.
- result.label = tf.cast(
- tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
- # 分类结果之后的数据代表图片,我们重新调整大小
- # The remaining bytes after the label represent the image, which we reshape
- # from [depth * height * width] to [depth, height, width].
- depth_major = tf.reshape(
- tf.strided_slice(record_bytes, [label_bytes],
- [label_bytes + image_bytes]),
- [result.depth, result.height, result.width])
- # 格式转换,从[颜色,高度,宽度]--》[高度,宽度,颜色]
- # Convert from [depth, height, width] to [height, width, depth].
- result.uint8image = tf.transpose(depth_major, [1, 2, 0])
- return result
- # 构建一个排列后的一组图片和分类
- def _generate_image_and_label_batch(image, label, min_queue_examples,
- batch_size, shuffle):
- # Create a queue that shuffles the examples, and then
- # read 'batch_size' images + labels from the example queue.
- # 线程数
- num_preprocess_threads = 8
- if shuffle:
- images, label_batch = tf.train.shuffle_batch(
- [image, label],
- batch_size=batch_size,
- num_threads=num_preprocess_threads,
- capacity=min_queue_examples + 3 * batch_size,
- min_after_dequeue=min_queue_examples)
- else:
- images, label_batch = tf.train.batch(
- [image, label],
- batch_size=batch_size,
- num_threads=num_preprocess_threads,
- capacity=min_queue_examples + 3 * batch_size)
- # Display the training images in the visualizer.
- tf.summary.image('images', images)
- return images, tf.reshape(label_batch, [batch_size])
- # 为CIFAR评价构建输入
- # data_dir路径
- # batch_size一个组的大小
- def distorted_inputs(data_dir, batch_size):
- filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
- for i in xrange(1, 6)]
- for f in filenames:
- if not tf.gfile.Exists(f):
- raise ValueError('Failed to find file: ' + f)
- # Create a queue that produces the filenames to read.
- filename_queue = tf.train.string_input_producer(filenames)
- # Read examples from files in the filename queue.
- read_input = read_cifar10(filename_queue)
- reshaped_image = tf.cast(read_input.uint8image, tf.float32)
- height = IMAGE_SIZE
- width = IMAGE_SIZE
- # Image processing for training the network. Note the many random
- # distortions applied to the image.
- # 随机裁剪图片
- # Randomly crop a [height, width] section of the image.
- distorted_image = tf.random_crop(reshaped_image, [height, width, 3])
- # 随机旋转图片
- # Randomly flip the image horizontally.
- distorted_image = tf.image.random_flip_left_right(distorted_image)
- # Because these operations are not commutative, consider randomizing
- # the order their operation.
- # 亮度变换
- distorted_image = tf.image.random_brightness(distorted_image,
- max_delta=63)
- # 对比度变换
- distorted_image = tf.image.random_contrast(distorted_image,
- lower=0.2, upper=1.8)
- # Subtract off the mean and divide by the variance of the pixels.
- # Linearly scales image to have zero mean and unit norm
- # 标准化
- float_image = tf.image.per_image_standardization(distorted_image)
- # Set the shapes of tensors.
- # 设置张量的型
- float_image.set_shape([height, width, 3])
- read_input.label.set_shape([1])
- # Ensure that the random shuffling has good mixing properties.
- # 确保洗牌的随机性
- min_fraction_of_examples_in_queue = 0.4
- min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
- min_fraction_of_examples_in_queue)
- print('Filling queue with %d CIFAR images before starting to train. '
- 'This will take a few minutes.' % min_queue_examples)
- # Generate a batch of images and labels by building up a queue of examples.
- return _generate_image_and_label_batch(float_image, read_input.label,
- min_queue_examples, batch_size,
- shuffle=True)
- # 为CIFAR评价构建输入
- # eval_data使用训练还是评价数据集
- # data_dir路径
- # batch_size一个组的大小
- def inputs(eval_data, data_dir, batch_size):
- if not eval_data:
- filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
- for i in xrange(1, 6)]
- num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
- else:
- filenames = [os.path.join(data_dir, 'test_batch.bin')]
- num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
- for f in filenames:
- if not tf.gfile.Exists(f):
- raise ValueError('Failed to find file: ' + f)
- # Create a queue that produces the filenames to read.
- # 文件名队列
- filename_queue = tf.train.string_input_producer(filenames)
- # Read examples from files in the filename queue.
- # 从文件中读取解析出的图片队列
- read_input = read_cifar10(filename_queue)
- # 转换为float
- reshaped_image = tf.cast(read_input.uint8image, tf.float32)
- height = IMAGE_SIZE
- width = IMAGE_SIZE
- # Image processing for evaluation.
- # Crop the central [height, width] of the image.
- # 剪切图片的中心
- resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
- height, width)
- # Subtract off the mean and divide by the variance of the pixels.
- # 标准化图片
- float_image = tf.image.per_image_standardization(resized_image)
- # Set the shapes of tensors.
- # 设置张量的型
- float_image.set_shape([height, width, 3])
- read_input.label.set_shape([1])
- # Ensure that the random shuffling has good mixing properties.
- # 确保洗牌的随机性
- min_fraction_of_examples_in_queue = 0.4
- min_queue_examples = int(num_examples_per_epoch *
- min_fraction_of_examples_in_queue)
- # Generate a batch of images and labels by building up a queue of examples.
- return _generate_image_and_label_batch(float_image, read_input.label,
- min_queue_examples, batch_size,
- shuffle=False)
Tensorflow样例代码分析cifar10的更多相关文章
- TensorFlow入门之MNIST样例代码分析
这几天想系统的学习一下TensorFlow,为之后的工作打下一些基础.看了下<TensorFlow:实战Google深度学习框架>这本书,目前个人觉得这本书还是对初学者挺友好的,作者站在初 ...
- amaze样例页面分析(一)
amaze样例页面分析(一) 一.总结 1.从审查(inspect)中是很清楚的可以弄清楚这些part之间的结构关系的 2.一者在于弄清楚他们之间的结构关系,二者在于知道结构的每一部分是干嘛的 3.i ...
- 使用ffmpeg实现转码样例(代码实现)
分类: C/C++ 使用ffmpeg实现转码样例(代码实现) 使用ffmpeg转码主要工作如下: Demux -> Decoding -> Encoding -> Muxing 其中 ...
- java 线程、线程池基本应用演示样例代码回想
java 线程.线程池基本应用演示样例代码回想 package org.rui.thread; /** * 定义任务 * * @author lenovo * */ public class Lift ...
- ECharts组件应用样例代码
一.从Echarts官网上下载最新版本组件 Echarts是百度开发的开源Web图表组件,界面美观,使用简单.组件下载地址:http://echarts.baidu.com/echarts2/doc/ ...
- java文件夹相关操作 演示样例代码
java文件夹相关操作 演示样例代码 package org.rui.io; import java.io.File; import java.io.FilenameFilter; import ja ...
- 10分钟理解Android数据库的创建与使用(附具体解释和演示样例代码)
1.Android数据库简单介绍. Android系统的framework层集成了Sqlite3数据库.我们知道Sqlite3是一种轻量级的高效存储的数据库. Sqlite数据库具有以下长处: (1) ...
- C#调用 Oracle 存储过程样例代码
-- 建表 CREATE TABLE sale_report ( sale_date DATE NOT NULL , sale_item VARCHAR(2) NOT NULL , ...
- java 又一次抛出异常 相关处理结果演示样例代码
java 又一次抛出异常 相关处理结果演示样例代码 package org.rui.ExceptionTest; /** * 又一次抛出异常 * 在某些情况下,我们想又一次掷出刚才产生过的违例,特别是 ...
随机推荐
- 深入浅出Java多线程(2)-Swing中的EDT(事件分发线程) [转载]
本系列文章导航 深入浅出Java多线程(1)-方法 join 深入浅出Java多线程(2)-Swing中的EDT(事件分发线程) 深入浅出多线程(3)-Future异步模式以及在JDK1.5Concu ...
- 20、Semantic-UI之数据验证
20.1 实现数据验证 在很多前端框架中都提供了数据验证的操作,比如jQuery的验证框架等,但是jQuery的验证框架js文件太多:在使用Semantic-UI框架的时候只需要导入semanti ...
- ListControl的用法
ListControl 控件可在窗体中管理和显示列 表项.可控制列表内容的显示方式,能够以图标和表格的形式显示数据.打开ListControl控件的属性窗口,在Styles选项卡中的View属性中 可 ...
- 强大的CSS 属性选择符 配合 stylish 屏蔽新浪微博信息流广告
新建一条微博域名下的规则: @-moz-document domain("weibo.com") { #v6_pl_rightmod_rank,#v6_pl_rightmod_ad ...
- 曲苑杂坛--查看CPU配置
--===================================================--查看CPU配置SELECT cpu_count AS [Logical CPU Coun ...
- SQL 语句case when
简介 case when 一般有两种书写方式,多用于查询判断 1. case 列名 when '' then '空' ' then '成功' ' then '失败' else '其他' end as ...
- 小修改,让mvc的验证锦上添点花(1)
首先,mvc的客户端验证用的是jquery.validate.js, jquery.validate本身已经提供了很好的扩展功能,通过简单点配置就可以做得更好看些. 而Microsoft通过jquer ...
- Weekly Contest 121
984. String Without AAA or BBB Given two integers A and B, return any string S such that: S has leng ...
- “全栈2019”Java第四十二章:静态代码块与初始化顺序
难度 初级 学习时间 10分钟 适合人群 零基础 开发语言 Java 开发环境 JDK v11 IntelliJ IDEA v2018.3 文章原文链接 "全栈2019"Java第 ...
- PTA 7-2 深入虎穴 (30 分)
著名的王牌间谍 007 需要执行一次任务,获取敌方的机密情报.已知情报藏在一个地下迷宫里,迷宫只有一个入口,里面有很多条通路,每条路通向一扇门.每一扇门背后或者是一个房间,或者又有很多条路,同样是每条 ...