Caffe代码导读(4):数据集准备
转载自:
Caffe代码导读(4):数据集准备 - 卜居 - 博客频道 - CSDN.NET
http://blog.csdn.net/kkk584520/article/details/41649281
Caffe上面有两个比较简单的例子:MNIST和CIFAR-10,前者是用于手写数字识别的,后者用于小图片分类。这两个数据集可以在Caffe源码框架中用脚本(CAFFE_ROOT/data/mnist/get_mnist.sh和CAFFE_ROOT/data/cifar10/get_cifar10.sh)下载,如下图所示:
- $ ./get_cifar10.sh
- Downloading...
- --2014-12-02 01:20:12-- http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz
- Resolving www.cs.toronto.edu... 128.100.3.30
- Connecting to www.cs.toronto.edu|128.100.3.30|:80... connected.
- HTTP request sent, awaiting response... 200 OK
- Length: 170052171 (162M) [application/x-gzip]
- Saving to: “cifar-10-binary.tar.gz”
- 100%[===========================================================================================================================================================>] 170,052,171 859K/s in 2m 16s
- 2014-12-02 01:22:28 (1.20 MB/s) - “cifar-10-binary.tar.gz” saved [170052171/170052171]
- Unzipping...
- Done.
- $ ls
- batches.meta.txt data_batch_1.bin data_batch_2.bin data_batch_3.bin data_batch_4.bin data_batch_5.bin get_cifar10.sh readme.html test_batch.bin
$ ./get_cifar10.sh
Downloading...
--2014-12-02 01:20:12-- http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz
Resolving www.cs.toronto.edu... 128.100.3.30
Connecting to www.cs.toronto.edu|128.100.3.30|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 170052171 (162M) [application/x-gzip]
Saving to: “cifar-10-binary.tar.gz”100%[===========================================================================================================================================================>] 170,052,171 859K/s in 2m 16s2014-12-02 01:22:28 (1.20 MB/s) - “cifar-10-binary.tar.gz” saved [170052171/170052171]Unzipping...
Done.
$ ls
batches.meta.txt data_batch_1.bin data_batch_2.bin data_batch_3.bin data_batch_4.bin data_batch_5.bin get_cifar10.sh readme.html test_batch.bin
- $ ./get_mnist.sh
- Downloading...
- --2014-12-02 01:24:25-- http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz
- Resolving yann.lecun.com... 128.122.47.89
- Connecting to yann.lecun.com|128.122.47.89|:80... connected.
- HTTP request sent, awaiting response... 200 OK
- Length: 9912422 (9.5M) [application/x-gzip]
- Saving to: “train-images-idx3-ubyte.gz”
- 100%[===========================================================================================================================================================>] 9,912,422 2.09M/s in 6.7s
- 2014-12-02 01:24:33 (1.42 MB/s) - “train-images-idx3-ubyte.gz” saved [9912422/9912422]
- --2014-12-02 01:24:33-- http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
- Resolving yann.lecun.com... 128.122.47.89
- Connecting to yann.lecun.com|128.122.47.89|:80... connected.
- HTTP request sent, awaiting response... 200 OK
- Length: 28881 (28K) [application/x-gzip]
- Saving to: “train-labels-idx1-ubyte.gz”
- 100%[===========================================================================================================================================================>] 28,881 42.0K/s in 0.7s
- 2014-12-02 01:24:34 (42.0 KB/s) - “train-labels-idx1-ubyte.gz” saved [28881/28881]
- --2014-12-02 01:24:34-- http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
- Resolving yann.lecun.com... 128.122.47.89
- Connecting to yann.lecun.com|128.122.47.89|:80... connected.
- HTTP request sent, awaiting response... 200 OK
- Length: 1648877 (1.6M) [application/x-gzip]
- Saving to: “t10k-images-idx3-ubyte.gz”
- 100%[===========================================================================================================================================================>] 1,648,877 552K/s in 2.9s
- 2014-12-02 01:24:39 (552 KB/s) - “t10k-images-idx3-ubyte.gz” saved [1648877/1648877]
- --2014-12-02 01:24:39-- http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
- Resolving yann.lecun.com... 128.122.47.89
- Connecting to yann.lecun.com|128.122.47.89|:80... connected.
- HTTP request sent, awaiting response... 200 OK
- Length: 4542 (4.4K) [application/x-gzip]
- Saving to: “t10k-labels-idx1-ubyte.gz”
- 100%[===========================================================================================================================================================>] 4,542 19.8K/s in 0.2s
- 2014-12-02 01:24:40 (19.8 KB/s) - “t10k-labels-idx1-ubyte.gz” saved [4542/4542]
- Unzipping...
- Done.
- $ ls
- get_mnist.sh t10k-images-idx3-ubyte t10k-labels-idx1-ubyte train-images-idx3-ubyte train-labels-idx1-ubyte
$ ./get_mnist.sh
Downloading...
--2014-12-02 01:24:25-- http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 9912422 (9.5M) [application/x-gzip]
Saving to: “train-images-idx3-ubyte.gz”100%[===========================================================================================================================================================>] 9,912,422 2.09M/s in 6.7s2014-12-02 01:24:33 (1.42 MB/s) - “train-images-idx3-ubyte.gz” saved [9912422/9912422]--2014-12-02 01:24:33-- http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 28881 (28K) [application/x-gzip]
Saving to: “train-labels-idx1-ubyte.gz”100%[===========================================================================================================================================================>] 28,881 42.0K/s in 0.7s2014-12-02 01:24:34 (42.0 KB/s) - “train-labels-idx1-ubyte.gz” saved [28881/28881]--2014-12-02 01:24:34-- http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1648877 (1.6M) [application/x-gzip]
Saving to: “t10k-images-idx3-ubyte.gz”100%[===========================================================================================================================================================>] 1,648,877 552K/s in 2.9s2014-12-02 01:24:39 (552 KB/s) - “t10k-images-idx3-ubyte.gz” saved [1648877/1648877]--2014-12-02 01:24:39-- http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
Resolving yann.lecun.com... 128.122.47.89
Connecting to yann.lecun.com|128.122.47.89|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 4542 (4.4K) [application/x-gzip]
Saving to: “t10k-labels-idx1-ubyte.gz”100%[===========================================================================================================================================================>] 4,542 19.8K/s in 0.2s2014-12-02 01:24:40 (19.8 KB/s) - “t10k-labels-idx1-ubyte.gz” saved [4542/4542]Unzipping...
Done.
$ ls
get_mnist.sh t10k-images-idx3-ubyte t10k-labels-idx1-ubyte train-images-idx3-ubyte train-labels-idx1-ubyte
如果你下载出现问题可以从我的资源处获取,网址http://download.csdn.net/detail/kkk584520/8213463。
原始数据集为二进制文件,需要转换为leveldb或lmdb才能被Caffe识别。转换格式的工具已经集成在Caffe代码中,见CAFFE_ROOT/examples/mnist/convert_mnist_data.cpp
和CAFFE_ROOT/examples/cifar10/convert_cifar_data.cpp,如果对leveldb或lmdb操作不熟悉可以从这两个源代码中学习。我们只需要在CAFFE_ROOT目录中执行两条命令即可:
./examples/mnist/create_mnist.sh
./examples/cifar10/create_cifar10.sh
Caffe代码导读(4):数据集准备相关推荐
- Caffe代码导读(5):对数据集进行Testing
转载自: Caffe代码导读(5):对数据集进行Testing - 卜居 - 博客频道 - CSDN.NET http://blog.csdn.net/kkk584520/article/detail ...
- Caffe代码导读(1):Protobuf例子
转载自: Caffe代码导读(1):Protobuf例子 - 卜居 - 博客频道 - CSDN.NET http://blog.csdn.net/kkk584520/article/details/4 ...
- Caffe代码导读(0):路线图
转载自: Caffe代码导读(0):路线图 - 卜居 - 博客频道 - CSDN.NET http://blog.csdn.net/kkk584520/article/details/41681085 ...
- Caffe代码导读(3):LevelDB例程
Caffe自带例子Cifar10中使用leveldb存储输入数据,为此我们研究一下怎样使用它.安装步骤可以参考http://blog.csdn.net/kangqing2003/article/det ...
- Caffe代码导读(2):LMDB简介
闪电般的内存映射型数据库管理(LMDB) 简介 LMDB是基于二叉树的数据库管理库,建模基于伯克利数据库的应用程序接口,但做了大幅精简.整个数据库都是内存映射型的,所有数据获取返回数据都是直接从映射的 ...
- Android工具HierarchyViewer 代码导读(3) -- 后台代码
在上文中,我们讲解了如何把HierarchyViewer的项目导入到Eclipse中,以便更高效阅读代码.本文将讲解HierarchyViewer的后台代码,建议大家可以先阅读<Android工 ...
- Python编写caffe代码
有时候,我们需要将网络使用caffe代码实现,人工手写容易出问题.可以使用Python完成网络编写. 卷积层: def generate_conv_layer_no_bias(name, bottom ...
- 语义级代码克隆检测数据集的评估与改进
摘要:应用深度学习来检测语义代码克隆受到了研究界的广泛关注. 本文分享自华为云社区<语义级代码克隆检测数据集的评估与改进>,作者:软件分析Lab. 一.背景介绍 代码克隆检测[1]是软件工 ...
- DirectFB代码导读
DirectFB代码导读 转载时请注明出处和作者联系方式 作者联系方式:李先静 <xianjimli at hotmail dot com> DirectFB是一个庞大的系统,对它进行彻底 ...
最新文章
- 用C/C++编写window服务
- poj1061-青蛙的约会(拓展欧几里得java)
- github怎么删除已经发布的Releases
- 「软件项目管理」一文详解软件项目质量计划
- NXP UWB NCJ29D5开发(二)BlinkyLed例程
- 单链表(不带头结点)
- centos7 如何使用ReaR进行系统备份(如何使用NFS方法设置ReaR备份)
- 计算机科技兴趣小组活动总结,信息技术兴趣小组活动总结
- ITIL4定义的四大价值维度
- 视频压制探索与B站视频压制参数解析
- AD16常用命令高效编辑命令
- VTK(The Visualization Toolkit)加载stl模型
- linux下php添加imap模块
- Kafka入门教程(一)
- Python官网主页改版 http://www.python.org/
- STM32 四轴无人机的设计——基于HCSR04超声波模块的距离检测与警报设计
- Github页面图片无法显示Github页面访问不了
- 新东方雅思词汇(List 6 ~ List 10)
- 2016百度之星 - 测试赛(热身,陈题)-列变位法解密(模拟)
- Android 项目集成 Freeline
热门文章
- Spring @Resource、@Autowired、@Qualifier区别
- Writing Images to the Excel Sheet using PHPExcel--转载
- Linux 进程管理剖析--转
- 反欺诈评分模型之手机终端
- Transformer-XL解读(论文 + PyTorch源码)
- Hive和HBase
- CAFFE学习笔记(一)Caffe_Example之训练mnist
- 年终盘点:2015年人工智能的五大关键词
- 实战并发编程 - 09多线程Guarded Suspension模式案例实战
- Apache ZooKeeper - 使用Apache Curator操作ZK