# Yolo_mark
**Windows** & **Linux** GUI for marking bounded boxes of objects in images for training Yolo v3 and v2
* To compile on **Windows** open `yolo_mark.sln` in MSVS2013/2015, compile it **x64 & Release** and run the file: `x64/Release/yolo_mark.cmd`. Change paths in `yolo_mark.sln` to the OpenCV 2.x/3.x installed on your computer:
* (right click on project) -> properties -> C/C++ -> General -> Additional Include Directories: `C:\opencv_3.0\opencv\build\include;`
* (right click on project) -> properties -> Linker -> General -> Additional Library Directories: `C:\opencv_3.0\opencv\build\x64\vc14\lib;`
* To compile on **Linux** type in console 3 commands:
```
cmake .
make
./linux_mark.sh
```
Supported both: OpenCV 2.x and OpenCV 3.x
--------
1. To test, simply run
* **on Windows:** `x64/Release/yolo_mark.cmd`
* **on Linux:** `./linux_mark.sh`
2. To use for labeling your custom images:
* delete all files from directory `x64/Release/data/img`
* put your `.jpg`-images to this directory `x64/Release/data/img`
* change numer of classes (objects for detection) in file `x64/Release/data/obj.data`: https://github.com/AlexeyAB/Yolo_mark/blob/master/x64/Release/data/obj.data#L1
* put names of objects, one for each line in file `x64/Release/data/obj.names`: https://github.com/AlexeyAB/Yolo_mark/blob/master/x64/Release/data/obj.names
* run file: `x64\Release\yolo_mark.cmd`
3. To training for your custom objects, you should change 2 lines in file `x64/Release/yolo-obj.cfg`:
* set number of classes (objects): https://github.com/AlexeyAB/Yolo_mark/blob/master/x64/Release/yolo-obj.cfg#L230
* set `filter`-value
* For Yolov2 `(classes + 5)*5`: https://github.com/AlexeyAB/Yolo_mark/blob/master/x64/Release/yolo-obj.cfg#L224
* For Yolov3 `(classes + 5)*3`
3.1 Download pre-trained weights for the convolutional layers (76 MB): http://pjreddie.com/media/files/darknet19_448.conv.23
3.2 Put files: `yolo-obj.cfg`, `data/train.txt`, `data/obj.names`, `data/obj.data`, `darknet19_448.conv.23` and directory `data/img` near with executable `darknet`-file, and start training: `darknet detector train data/obj.data yolo-obj.cfg darknet19_448.conv.23`
For a detailed description, see: https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects
----
#### How to get frames from videofile:
To get frames from videofile (save each N frame, in example N=10), you can use this command:
* on Windows: `yolo_mark.exe data/img cap_video test.mp4 10`
* on Linux: `./yolo_mark x64/Release/data/img cap_video test.mp4 10`
Directory `data/img` should be created before this. Also on Windows, the file `opencv_ffmpeg340_64.dll` from `opencv\build\bin` should be placed near with `yolo_mark.exe`.
As a result, many frames will be collected in the directory `data/img`. Then you can label them manually using such command:
* on Windows: `yolo_mark.exe data/img data/train.txt data/obj.names`
* on Linux: `./yolo_mark x64/Release/data/img x64/Release/data/train.txt x64/Release/data/obj.names`
----
#### Here are:
* /x64/Release/
* `yolo_mark.cmd` - example hot to use yolo mark: `yolo_mark.exe data/img data/train.txt data/obj.names`
* `train_obj.cmd` - example how to train yolo for your custom objects (put this file near with darknet.exe): `darknet.exe detector train data/obj.data yolo-obj.cfg darknet19_448.conv.23`
* `yolo-obj.cfg` - example of yoloV3-neural-network for 2 object
* /x64/Release/data/
* `obj.names` - example of list with object names
* `obj.data` - example with configuration for training Yolo v3
* `train.txt` - example with list of image filenames for training Yolo v3
* /x64/Release/data/img/`air4.txt` - example with coordinates of objects on image `air4.jpg` with aircrafts (class=0)
![Image of Yolo_mark](https://habrastorage.org/files/229/f06/277/229f06277fcc49279342b7edfabbb47a.jpg)
### Instruction manual
#### Mouse control
Button | Description |
--- | --- |
Left | Draw box
Right | Move box
#### Keyboard Shortcuts
Shortcut | Description |
--- | --- |
<kbd>→</kbd> | Next image |
<kbd>←</kbd> | Previous image |
<kbd>r</kbd> | Delete selected box (mouse hovered) |
<kbd>c</kbd> | Clear all marks on the current image |
<kbd>p</kbd> | Copy previous mark |
<kbd>o</kbd> | Track objects |
<kbd>ESC</kbd> | Close application |
<kbd>n</kbd> | One object per image |
<kbd>0-9</kbd> | Object id |
<kbd>m</kbd> | Show coords |
<kbd>w</kbd> | Line width |
<kbd>k</kbd> | Hide object name |
<kbd>h</kbd> | Help |
没有合适的资源?快使用搜索试试~ 我知道了~
编译好的windows yolo-mark
共39个文件
tlog:7个
txt:5个
png:3个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 2 下载量 133 浏览量
2022-06-15
19:52:55
上传
评论
收藏 10.69MB 7Z 举报
温馨提示
编译好的windows yolo-mark
资源推荐
资源详情
资源评论
收起资源包目录
Yolo_mark-master.7z (39个子文件)
Yolo_mark-master
.vs
yolo_mark
v15
Browse.VC.db 44.25MB
.suo 26KB
yolo_mark.vcxproj.user 165B
yolo_mark.vcxproj 7KB
yolo_mark.sln 1KB
LICENSE 1KB
linux_mark.sh 173B
x64
Release
data
img
00002000_640x480.png 303KB
00002000_640x480.txt 780B
00004000_640x480.txt 858B
00004000_640x480.png 304KB
00000000_640x480.png 289KB
00000000_640x480.txt 858B
obj.names 8B
train.txt 93B
obj.data 100B
yolo_mark.log 3KB
yolo_mark.ipdb 903KB
yolo_mark.cmd 138B
main.obj 5.69MB
yolo_mark.iobj 2.81MB
train_obj.cmd 166B
yolo-obj.cfg 2KB
yolo_mark.tlog
CL.write.1.tlog 402B
CL.read.1.tlog 46KB
CL.command.1.tlog 724B
link.write.1.tlog 444B
link.command.1.tlog 1KB
link.read.1.tlog 3KB
yolo_mark.lastbuildstate 223B
yolo_mark.write.1u.tlog 442B
yolo_mark.exe 113KB
yolo_mark.pdb 3.3MB
vc141.pdb 2.25MB
Debug
yolo_mark.log 456B
main.cpp 38KB
.gitignore 84B
CMakeLists.txt 304B
README.md 4KB
共 39 条
- 1
资源评论
- qq_297711012022-11-03资源中能够借鉴的内容很多,值得学习的地方也很多,大家一起进步!
- baoyingzhi12342022-12-23资源和描述一致,质量不错,解决了我的问题,感谢资源主。
coder_small_bell
- 粉丝: 266
- 资源: 30
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 2022NOC软件创意编程赛项真题python小学高年级-决赛(有解析)
- mathml转换latex需要的xsl文件
- 2022NOC软件创意编程赛项真题图形化小学高年级-决赛赛(有解析)
- gbase驱动下载gbase-connector-java-8.3.81.53驱动下载
- 2022NOC软件创意编程赛项真题图形化小学低年级-决赛赛(有解析)
- InsightFace从青铜到王者,超大规模人脸识别的优雅解法
- python后端开发spider框架详解
- 基于 STM32 与 ESP8266 的智能家居系统源码.zip
- 毕业设计:基于SSM的mysql-个性化点餐配送系统(源码 + 数据库 + 说明文档)
- 基于matlab的鱼苗计数识别(GUI界面).zip代码57
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功