darknet-master
所属分类:人工智能/神经网络/深度学习
开发工具:Python
文件大小:4674KB
下载次数:12
上传日期:2018-05-14 20:17:49
上 传 者:
longlongman
说明: yolo网络的实现,基本可以做到实时视频物体识别
(The realization of Yolo network can basically achieve real-time video object recognition.)
文件列表:
.circleci (0, 2017-11-21)
.circleci\config.yml (253, 2017-11-21)
3rdparty (0, 2017-11-21)
3rdparty\dll (0, 2017-11-21)
3rdparty\dll\x64 (0, 2017-11-21)
3rdparty\dll\x64\pthreadGC2.dll (185976, 2017-11-21)
3rdparty\dll\x64\pthreadVC2.dll (82944, 2017-11-21)
3rdparty\dll\x86 (0, 2017-11-21)
3rdparty\dll\x86\pthreadGC2.dll (119888, 2017-11-21)
3rdparty\dll\x86\pthreadGCE2.dll (121953, 2017-11-21)
3rdparty\dll\x86\pthreadVC2.dll (55808, 2017-11-21)
3rdparty\dll\x86\pthreadVCE2.dll (61952, 2017-11-21)
3rdparty\dll\x86\pthreadVSE2.dll (57344, 2017-11-21)
3rdparty\include (0, 2017-11-21)
3rdparty\include\pthread.h (42499, 2017-11-21)
3rdparty\include\sched.h (4995, 2017-11-21)
3rdparty\include\semaphore.h (4563, 2017-11-21)
3rdparty\lib (0, 2017-11-21)
3rdparty\lib\x64 (0, 2017-11-21)
3rdparty\lib\x64\libpthreadGC2.a (93692, 2017-11-21)
3rdparty\lib\x64\pthreadVC2.lib (29738, 2017-11-21)
3rdparty\lib\x86 (0, 2017-11-21)
3rdparty\lib\x86\libpthreadGC2.a (93480, 2017-11-21)
3rdparty\lib\x86\libpthreadGCE2.a (93486, 2017-11-21)
3rdparty\lib\x86\pthreadVC2.lib (30334, 2017-11-21)
3rdparty\lib\x86\pthreadVCE2.lib (30460, 2017-11-21)
3rdparty\lib\x86\pthreadVSE2.lib (30460, 2017-11-21)
LICENSE (515, 2017-11-21)
Makefile (2996, 2017-11-21)
build (0, 2017-11-21)
build\darknet (0, 2017-11-21)
build\darknet\darknet.sln (1283, 2017-11-21)
build\darknet\darknet.vcxproj (15700, 2017-11-21)
build\darknet\darknet_no_gpu.sln (1281, 2017-11-21)
build\darknet\darknet_no_gpu.vcxproj (15078, 2017-11-21)
build\darknet\x64 (0, 2017-11-21)
build\darknet\x64\backup (0, 2017-11-21)
... ...
# Yolo-v2 Windows and Linux version
[![CircleCI](https://circleci.com/gh/AlexeyAB/darknet.svg?style=svg)](https://circleci.com/gh/AlexeyAB/darknet)
1. [How to use](#how-to-use)
2. [How to compile on Linux](#how-to-compile-on-linux)
3. [How to compile on Windows](#how-to-compile-on-windows)
4. [How to train (Pascal VOC Data)](#how-to-train-pascal-voc-data)
5. [How to train (to detect your custom objects)](#how-to-train-to-detect-your-custom-objects)
6. [When should I stop training](#when-should-i-stop-training)
7. [How to improve object detection](#how-to-improve-object-detection)
8. [How to mark bounded boxes of objects and create annotation files](#how-to-mark-bounded-boxes-of-objects-and-create-annotation-files)
9. [How to use Yolo as DLL](#how-to-use-yolo-as-dll)
| ![Darknet Logo](http://pjreddie.com/media/files/darknet-black-small.png) | ![map_fps](https://hsto.org/files/a24/21e/068/a2421e0689fb43f08584de9d44c2215f.jpg) https://arxiv.org/abs/1612.08242 |
|---|---|
| ![Darknet Logo](http://pjreddie.com/media/files/darknet-black-small.png) | ![map_fps](https://hsto.org/files/3a6/fdf/b53/3a6fdfb533f34cee9b52bdd9bb0b19d9.jpg) https://arxiv.org/abs/1612.08242 |
|---|---|
# "You Only Look Once: Unified, Real-Time Object Detection (version 2)"
A Yolo cross-platform Windows and Linux version (for object detection). Contributtors: https://github.com/pjreddie/darknet/graphs/contributors
This repository is forked from Linux-version: https://github.com/pjreddie/darknet
More details: http://pjreddie.com/darknet/yolo/
This repository supports:
* both Windows and Linux
* both OpenCV 3.x and OpenCV 2.4.13
* both cuDNN 5 and cuDNN 6
* CUDA >= 7.5
* also create SO-library on Linux and DLL-library on Windows
##### Requires:
* **Linux GCC>=4.9 or Windows MS Visual Studio 2015 (v140)**: https://go.microsoft.com/fwlink/?LinkId=532606&clcid=0x409 (or offline [ISO image](https://go.microsoft.com/fwlink/?LinkId=615448&clcid=0x409))
* **CUDA 8.0**: https://developer.nvidia.com/cuda-downloads
* **OpenCV 3.x**: https://sourceforge.net/projects/opencvlibrary/files/opencv-win/3.2.0/opencv-3.2.0-vc14.exe/download
* **or OpenCV 2.4.13**: https://sourceforge.net/projects/opencvlibrary/files/opencv-win/2.4.13/opencv-2.4.13.2-vc14.exe/download
- OpenCV allows to show image or video detection in the window and store result to file that specified in command line `-out_filename res.avi`
* **GPU with CC >= 2.0** if you use CUDA, or **GPU CC >= 3.0** if you use cuDNN + CUDA: https://en.wikipedia.org/wiki/CUDA#GPUs_supported
##### Pre-trained models for different cfg-files can be downloaded from (smaller -> faster & lower quality):
* `yolo.cfg` (194 MB COCO-model) - require 4 GB GPU-RAM: http://pjreddie.com/media/files/yolo.weights
* `yolo-voc.cfg` (194 MB VOC-model) - require 4 GB GPU-RAM: http://pjreddie.com/media/files/yolo-voc.weights
* `tiny-yolo.cfg` (60 MB COCO-model) - require 1 GB GPU-RAM: http://pjreddie.com/media/files/tiny-yolo.weights
* `tiny-yolo-voc.cfg` (60 MB VOC-model) - require 1 GB GPU-RAM: http://pjreddie.com/media/files/tiny-yolo-voc.weights
* `yolo9000.cfg` (186 MB Yolo9000-model) - require 4 GB GPU-RAM: http://pjreddie.com/media/files/yolo9000.weights
Put it near compiled: darknet.exe
You can get cfg-files by path: `darknet/cfg/`
##### Examples of results:
[![Everything Is AWESOME](http://img.youtube.com/vi/VOC3huqHrss/0.jpg)](https://www.youtube.com/watch?v=VOC3huqHrss "Everything Is AWESOME")
Others: https://www.youtube.com/channel/UC7ev3hNVkx4DzZ3LO19oebg
### How to use:
##### Example of usage in cmd-files from `build\darknet\x***\`:
* `darknet_voc.cmd` - initialization with 194 MB VOC-model yolo-voc.weights & yolo-voc.cfg and waiting for entering the name of the image file
* `darknet_demo_voc.cmd` - initialization with 194 MB VOC-model yolo-voc.weights & yolo-voc.cfg and play your video file which you must rename to: test.mp4
* `darknet_demo_store.cmd` - initialization with 194 MB VOC-model yolo-voc.weights & yolo-voc.cfg and play your video file which you must rename to: test.mp4, and store result to: res.avi
* `darknet_net_cam_voc.cmd` - initialization with 194 MB VOC-model, play video from network video-camera mjpeg-stream (also from you phone)
* `darknet_web_cam_voc.cmd` - initialization with 194 MB VOC-model, play video from Web-Camera number #0
* `darknet_coco_9000.cmd` - initialization with 186 MB Yolo9000 COCO-model, and show detection on the image: dog.jpg
* `darknet_coco_9000_demo.cmd` - initialization with 186 MB Yolo9000 COCO-model, and show detection on the video (if it is present): street4k.mp4, and store result to: res.avi
##### How to use on the command line:
On Linux use `./darknet` instead of `darknet.exe`, like this:`./darknet detector test ./cfg/coco.data ./cfg/yolo.cfg ./yolo.weights`
* 194 MB COCO-model - image: `darknet.exe detector test data/coco.data yolo.cfg yolo.weights -i 0 -thresh 0.2`
* Alternative method 194 MB COCO-model - image: `darknet.exe detect yolo.cfg yolo.weights -i 0 -thresh 0.2`
* 194 MB VOC-model - image: `darknet.exe detector test data/voc.data yolo-voc.cfg yolo-voc.weights -i 0`
* 194 MB COCO-model - video: `darknet.exe detector demo data/coco.data yolo.cfg yolo.weights test.mp4 -i 0`
* 194 MB VOC-model - video: `darknet.exe detector demo data/voc.data yolo-voc.cfg yolo-voc.weights test.mp4 -i 0`
* 194 MB COCO-model - **save result to the file res.avi**: `darknet.exe detector demo data/coco.data yolo.cfg yolo.weights test.mp4 -i 0 -out_filename res.avi`
* 194 MB VOC-model - **save result to the file res.avi**: `darknet.exe detector demo data/voc.data yolo-voc.cfg yolo-voc.weights test.mp4 -i 0 -out_filename res.avi`
* Alternative method 194 MB VOC-model - video: `darknet.exe yolo demo yolo-voc.cfg yolo-voc.weights test.mp4 -i 0`
* 60 MB VOC-model for video: `darknet.exe detector demo data/voc.data tiny-yolo-voc.cfg tiny-yolo-voc.weights test.mp4 -i 0`
* 194 MB COCO-model for net-videocam - Smart WebCam: `darknet.exe detector demo data/coco.data yolo.cfg yolo.weights http://192.168.0.80:8080/video?dummy=param.mjpg -i 0`
* 194 MB VOC-model for net-videocam - Smart WebCam: `darknet.exe detector demo data/voc.data yolo-voc.cfg yolo-voc.weights http://192.168.0.80:8080/video?dummy=param.mjpg -i 0`
* 194 MB VOC-model - WebCamera #0: `darknet.exe detector demo data/voc.data yolo-voc.cfg yolo-voc.weights -c 0`
* 186 MB Yolo9000 - image: `darknet.exe detector test cfg/combine9k.data yolo9000.cfg yolo9000.weights`
* 186 MB Yolo9000 - video: `darknet.exe detector demo cfg/combine9k.data yolo9000.cfg yolo9000.weights test.mp4`
* To process a list of images `image_list.txt` and save results of detection to `result.txt` use:
`darknet.exe detector test data/voc.data yolo-voc.cfg yolo-voc.weights < image_list.txt > result.txt`
You can comment this line so that each image does not require pressing the button ESC: https://github.com/AlexeyAB/darknet/blob/6ccb41808caf753feea58ca9df79d6367dedc434/src/detector.c#L509
##### For using network video-camera mjpeg-stream with any Android smartphone:
1. Download for Android phone mjpeg-stream soft: IP Webcam / Smart WebCam
* Smart WebCam - preferably: https://play.google.com/store/apps/details?id=com.acontech.android.SmartWebCam2
* IP Webcam: https://play.google.com/store/apps/details?id=com.pas.webcam
2. Connect your Android phone to computer by WiFi (through a WiFi-router) or USB
3. Start Smart WebCam on your phone
4. Replace the address below, on shown in the phone application (Smart WebCam) and launch:
* 194 MB COCO-model: `darknet.exe detector demo data/coco.data yolo.cfg yolo.weights http://192.168.0.80:8080/video?dummy=param.mjpg -i 0`
* 194 MB VOC-model: `darknet.exe detector demo data/voc.data yolo-voc.cfg yolo-voc.weights http://192.168.0.80:8080/video?dummy=param.mjpg -i 0`
### How to compile on Linux:
Just do `make` in the darknet directory.
Before make, you can set such options in the `Makefile`: [link](https://github.com/AlexeyAB/darknet/blob/9c1b9a2cf6363546c152251be578a21f3c3caec6/Makefile#L1)
* `GPU=1` to build with CUDA to accelerate by using GPU (CUDA should be in `/use/local/cuda`)
* `CUDNN=1` to build with cuDNN v5/v6 to accelerate training by using GPU (cuDNN should be in `/usr/local/cudnn`)
* `OPENCV=1` to build with OpenCV 3.x/2.4.x - allows to detect on video files and video streams from network cameras or web-cams
* `DEBUG=1` to bould debug version of Yolo
* `OPENMP=1` to build with OpenMP support to accelerate Yolo by using multi-core CPU
* `LIBSO=1` to build a library `darknet.so` and binary runable file `uselib` that uses this library. Or you can try to run so `LD_LIBRARY_PATH=./:$LD_LIBRARY_PATH ./uselib test.mp4` How to use this SO-library from your own code - you can look at C++ example: https://github.com/AlexeyAB/darknet/blob/master/src/yolo_console_dll.cpp
### How to compile on Windows:
1. If you have **MSVS 2015, CUDA 8.0 and OpenCV 3.0** (with paths: `C:\opencv_3.0\opencv\build\include` & `C:\opencv_3.0\opencv\build\x***\vc14\lib`), then start MSVS, open `build\darknet\darknet.sln`, set **x***** and **Release**, and do the: Build -> Build darknet
1.1. Find files `opencv_world320.dll` and `opencv_ffmpeg320_***.dll` in `C:\opencv_3.0\opencv\build\x***\vc14\bin` and put it near with `darknet.exe`
2. If you have other version of **CUDA (not 8.0)** then open `build\darknet\darknet.vcxproj` by using Notepad, find 2 places with "CUDA 8.0" and change it to your CUDA-version, then do step 1
3. If you **don't have GPU**, but have **MSVS 2015 and OpenCV 3.0** (with paths: `C:\opencv_3.0\opencv\build\include` & `C:\opencv_3.0\opencv\build\x***\vc14\lib`), then start MSVS, open `build\darknet\darknet_no_gpu.sln`, set **x***** and **Release**, and do the: Build -> Build darknet
4. If you have **OpenCV 2.4.13** instead of 3.0 then you should change pathes after `\darknet.sln` is opened
4.1 (right click on project) -> properties -> C/C++ -> General -> Additional Include Directories: `C:\opencv_2.4.13\opencv\build\include`
4.2 (right click on project) -> properties -> Linker -> General -> Additional Library Directories: `C:\opencv_2.4.13\opencv\build\x***\vc14\lib`
5. If you want to build with CUDNN to speed up then:
* download and install **cuDNN 6.0 for CUDA 8.0**: https://developer.nvidia.com/cudnn
* add Windows system variable `cudnn` with path to CUDNN: https://hsto.org/files/a49/3dc/fc4/a493dcfc4bd34a1295fd15e0e2e01f26.jpg
* open `\darknet.sln` -> (right click on project) -> properties -> C/C++ -> Preprocessor -> Preprocessor Definitions, and add at the beginning of line: `CUDNN;`
### How to compile (custom):
Also, you can to create your own `darknet.sln` & `darknet.vcxproj`, this example for CUDA 8.0 and OpenCV 3.0
Then add to your created project:
- (right click on project) -> properties -> C/C++ -> General -> Additional Include Directories, put here:
`C:\opencv_3.0\opencv\build\include;..\..\3rdparty\include;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir);$(cudnn)\include`
- (right click on project) -> Build dependecies -> Build Customizations -> set check on CUDA 8.0 or what version you have - for example as here: http://devblogs.nvidia.com/parallelforall/wp-content/uploads/2015/01/VS2013-R-5.jpg
- add to project all .c & .cu files from `\src`
- (right click on project) -> properties -> Linker -> General -> Additional Library Directories, put here:
`C:\opencv_3.0\opencv\build\x***\vc14\lib;$(CUDA_PATH)lib\$(PlatformName);$(cudnn)\lib\x***;%(AdditionalLibraryDirectories)`
- (right click on project) -> properties -> Linker -> Input -> Additional dependecies, put here:
`..\..\3rdparty\lib\x***\pthreadVC2.lib;cublas.lib;curand.lib;cudart.lib;cudnn.lib;%(AdditionalDependencies)`
- (right click on project) -> properties -> C/C++ -> Preprocessor -> Preprocessor Definitions
`OPENCV;_TIMESPEC_DEFINED;_CRT_SECURE_NO_WARNINGS;_CRT_RAND_S;WIN32;NDEBUG;_CONSOLE;_LIB;%(PreprocessorDefinitions)`
- open file: `\src\detector.c` and check lines `#pragma` and `#inclue` for OpenCV.
- compile to .exe (X*** & Release) and put .dll-s near with .exe:
* `pthreadVC2.dll, pthreadGC2.dll` from \3rdparty\dll\x***
* `cusolver***_80.dll, curand***_80.dll, cudart***_80.dll, cublas***_80.dll` - 80 for CUDA 8.0 or your version, from C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\bin
* For OpenCV 3.X: `opencv_world320.dll` and `opencv_ffmpeg320_***.dll` from `C:\opencv_3.0\opencv\build\x***\vc14\bin`
* For OpenCV 2.4.13: `opencv_core2413.dll`, `opencv_highgui2413.dll` and `opencv_ffmpeg2413_***.dll` from `C:\opencv_2.4.13\opencv\build\x***\vc14\bin`
## How to train (Pascal VOC Data):
1. Download pre-trained weights for the convolutional layers (76 MB): http://pjreddie.com/media/files/darknet19_448.conv.23 and put to the directory `build\darknet\x***`
2. Download The Pascal VOC Data and unpack it to directory `build\darknet\x***\data\voc` will be created dir `build\darknet\x***\data\voc\VOCdevkit\`:
* http://pjreddie.com/media/files/VOCtrainval_11-May-2012.tar
* http://pjreddie.com/media/files/VOCtrainval_06-Nov-2007.tar
* http://pjreddie.com/media/files/VOCtest_06-Nov-2007.tar
2.1 Download file `voc_label.py` to dir `build\darknet\x***\data\voc`: http://pjreddie.com/media/files/voc_label.py
3. Download and install Python for Windows: https://www.python.org/ftp/python/3.5.2/python-3.5.2-amd***.exe
4. Run command: `python build\darknet\x***\data\voc\voc_label.py` (to generate files: 2007_test.txt, 2007_train.txt, 2007_val.txt, 2012_train.txt, 2012_val.txt)
5. Run command: `type 2007_train.txt 2007_val.txt 2012_*.txt > train.txt`
6. Set `batch=***` and `subdivisions=8` in the file `yolo-voc.2.0.cfg`: [link](https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x***/yolo-voc.2.0.cfg#L2)
7. Start training by using `train_voc.cmd` or by using the command line: `darknet.exe detector train data/voc.data yolo-voc.2.0.cfg darknet19_448.conv.23`
If required change pathes in the file `build\darknet\x***\data\voc.data`
More information about training by the link: http://pjreddie.com/darknet/yolo/#train-voc
## How to train with multi-GPU:
1. Train it first on 1 GPU for like 1000 iterations: `darknet.exe detector train data/voc.data yolo-voc.2.0.cfg darknet19_448.conv.23`
2. Then stop and by using partially-trained model `/backup/yolo-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data yolo-voc.2.0.cfg /backup/yolo-voc_1000.weights -gpus 0,1,2,3`
https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ
## How to train (to detect your custom objects):
1. Create file `yolo-obj.cfg` with the same content as in `yolo-voc.2.0.cfg` (or copy `yolo-voc.2.0.cfg` to `yolo-obj.cfg)` and:
* change line batch to [`batch=***`](https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x***/yolo-voc.2.0.cfg#L2)
* change line subdivisions to [`subdivisions=8`](https://github.com/AlexeyAB/darknet/blob/master/build/darknet/x***/yolo-voc.2.0.cfg#L3)
* change line `classes=20` to your number of objects
* change line #237 from [`filters=125`](https://github.com/AlexeyAB/darknet/blob/master/cfg/yolo-voc.2.0.cfg#L224) to: filters=(classes + 5)*5
(Generally `filters` depends on the `classes`, `num` and `coords`, i.e. equal to `(classes + coords + 1)*num`)
So for example, for 2 objects, your file `yolo-obj.cfg` should differ from `yolo-voc.2.0.cfg` in such lines:
```
[convolutional]
filters=35
[region]
classes=2
```
2. Create file `obj.names` in the directory `build\darknet\x***\data\`, with objects names - each in new line
3. Create file `obj.data` in the directory `build\darknet\x***\data\`, containing (where **classes = number of objects**):
```
classes= 2
train = data/train.txt
valid = data/test.txt
names = data/obj.names
backup = backup/
```
4. Put image-files (.jpg) of your objects in the directory `build\darknet\x***\data\obj\`
5. Create `.txt`-file for each `.jpg`-image-file - in the same directory and with the same name, but with `.txt`-extension, and put to file: object number and object coordinates on this image, for each object in new line: `
`
Where:
* `` - integer number of object from `0` to `(classes-1)`
* ` ` - float values relative to width and height of image, it can be equal from 0.0 to 1.0
* for example: ` = / ` or ` = / `
* atention: ` ` - are center of rectangle (are not top-left corner)
For example for `img1.jpg` you should create `img1.txt` containing:
```
1 0.716797 0.395833 0.21***06 0.147222
0 0.687109 0.379167 0.255469 0.158333
1 0.420312 0.395833 0.140625 0.166667
```
6. Create file `train.txt` in directory `build\darknet\x***\data\`, with filenames of your images, each filename in new line, with path relative to `darknet.exe`, for example containing:
```
data/obj/img1.jpg
data/obj/img2.jpg
data/obj/img3.jpg
```
7. Download pre-trained weights for the convolutional layers (76 MB): http://pjreddie.com/media/files/darknet19_448.conv.23 and put to the directory `build\darknet\x***`
8. Start training by using the command line: `darknet.exe detector train data/obj.data yolo-obj.cfg darknet19_448.conv.23`
(file `yolo-obj_xxx.weights` will be saved to the `build\darknet\x***\backup\` for each 100 iterations until 1000 iterations has been reached, and after for each 1000 iterations)
9. After training is complete - get result `yolo-obj_final.weights` from path `build\darknet\x***\backup\`
* After each 1000 iterations you can stop and later start training from this point. For example, after 2000 iterations you can stop training, and later just copy `yolo-obj_2000.weights` from `build\darknet\x***\backup\` to `build\darknet\x***\` and start training using: `darknet.exe detector train data/obj.data yolo-obj.cfg yolo-obj_2000.weights`
* Also you can get result earlier than all 45000 iterations.
## When should I stop training:
Usually sufficient 2000 iterations for each class(object). But for a more precise definition when you should stop training, use the following manual:
1. During training, you will see varying indicators of error, and you should stop when no longer decreases **0.060730 avg**:
> Region Avg IOU: 0.7***363, Class: 0.893232, Obj: 0.700808, No Obj: 0.004567, Avg Recall: 1.000000, count: 8
> Region Avg IOU: 0.800677, Class: 0.892181, Obj: 0.701590, No Obj: 0.004574, Avg Recall: 1.000000, count: 8
>
> **9002**: 0.211667, **0.060730 avg**, 0.001000 rate, 3.868000 seconds, 576128 images
> Loaded: 0.000000 seconds
* **9002** - iteration number (number of batch)
* **0.060730 avg** - average loss (error) - **the lower, the better**
When you see that average loss **0.xxxxxx avg** no longer decreases at many iterations then you should stop training.
2. Once training is stopped, you should take some of last `.weights`-files from `darknet\build\darknet\x***\backup` and choose the best of them:
For example, you stopped training after 9000 iterations, but the best result can give one of previous weights (7000, 8000, 9000). It can happen due to overfitting. **Overfitting** - is case when you can detect objects on images from training-dataset, but can't detect ojbects on any others images. You should get weights from **Early Stopping Point**:
![Overfitting](https://hsto.org/files/5dc/7ae/7fa ... ...
近期下载者:
相关文件:
收藏者: