win10+cuda10.2+VS2019+YOLOV4.zip

# Yolo-v4 and Yolo-v3/v2 for Windows and Linux ### (neural network for object detection) - Tensor Cores can be used on [Linux](https://github.com/AlexeyAB/darknet#how-to-compile-on-linux) and [Windows](https://github.com/AlexeyAB/darknet#how-to-compile-on-windows-using-cmake-gui) Paper Yolo v4: https://arxiv.org/abs/2004.10934 More details: http://pjreddie.com/darknet/yolo/ [](https://circleci.com/gh/AlexeyAB/darknet) [](https://travis-ci.org/AlexeyAB/darknet) [](https://ci.appveyor.com/project/AlexeyAB/darknet/branch/master) [](https://github.com/AlexeyAB/darknet/graphs/contributors) [](https://github.com/AlexeyAB/darknet/blob/master/LICENSE) [](https://zenodo.org/badge/latestdoi/75388965) * [Requirements (and how to install dependecies)](#requirements) * [Pre-trained models](#pre-trained-models) * [Explanations in issues](https://github.com/AlexeyAB/darknet/issues?q=is%3Aopen+is%3Aissue+label%3AExplanations) * [Yolo v3 in other frameworks (TensorRT, TensorFlow, PyTorch, OpenVINO, OpenCV-dnn, TVM,...)](#yolo-v3-in-other-frameworks) * [Datasets](#datasets) 0. [Improvements in this repository](#improvements-in-this-repository) 1. [How to use](#how-to-use-on-the-command-line) 2. How to compile on Linux * [Using cmake](#how-to-compile-on-linux-using-cmake) * [Using make](#how-to-compile-on-linux-using-make) 3. How to compile on Windows * [Using CMake-GUI](#how-to-compile-on-windows-using-cmake-gui) * [Using vcpkg](#how-to-compile-on-windows-using-vcpkg) * [Legacy way](#how-to-compile-on-windows-legacy-way) 4. [How to train (Pascal VOC Data)](#how-to-train-pascal-voc-data) 5. [How to train with multi-GPU:](#how-to-train-with-multi-gpu) 6. [How to train (to detect your custom objects)](#how-to-train-to-detect-your-custom-objects) 7. [How to train tiny-yolo (to detect your custom objects)](#how-to-train-tiny-yolo-to-detect-your-custom-objects) 8. [When should I stop training](#when-should-i-stop-training) 9. [How to calculate mAP on PascalVOC 2007](#how-to-calculate-map-on-pascalvoc-2007) 10. [How to improve object detection](#how-to-improve-object-detection) 11. [How to mark bounded boxes of objects and create annotation files](#how-to-mark-bounded-boxes-of-objects-and-create-annotation-files) 12. [How to use Yolo as DLL and SO libraries](#how-to-use-yolo-as-dll-and-so-libraries) |  | &nbsp;  AP50:95 / AP50 - FPS (Tesla V100) Paper: https://arxiv.org/abs/2004.10934 | |---|---| * Yolo v4 Full comparison: [map_fps](https://user-images.githubusercontent.com/4096485/80213824-6e9d7d80-8642-11ea-94a6-0be90c7d7cd5.png) * CSPNet: [map_fps](https://user-images.githubusercontent.com/4096485/71702416-6645dc00-2de0-11ea-8d65-de7d4b604021.png) [paper](https://arxiv.org/abs/1911.11929) Comparison: https://github.com/WongKinYiu/CrossStagePartialNetworks * Yolo v3 on MS COCO: [Speed / Accuracy (mAP@0.5) chart](https://user-images.githubusercontent.com/4096485/52151356-e5d4a380-2683-11e9-9d7d-ac7bc192c477.jpg) * Yolo v3 on MS COCO (Yolo v3 vs RetinaNet) - Figure 3: https://arxiv.org/pdf/1804.02767v1.pdf * Yolo v2 on Pascal VOC 2007: https://hsto.org/files/a24/21e/068/a2421e0689fb43f08584de9d44c2215f.jpg * Yolo v2 on Pascal VOC 2012 (comp4): https://hsto.org/files/3a6/fdf/b53/3a6fdfb533f34cee9b52bdd9bb0b19d9.jpg #### How to evaluate AP of YOLOv4 on the MS COCO evaluation server 1. Download and unzip test-dev2017 dataset from MS COCO server: http://images.cocodataset.org/zips/test2017.zip 2. Download list of images for Detection taks and replace the paths with yours: https://raw.githubusercontent.com/AlexeyAB/darknet/master/scripts/testdev2017.txt 3. Download `yolov4.weights` file: https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT 4. Content of the file `cfg/coco.data` should be ``` classes= 80 train = <replace with your path>/trainvalno5k.txt valid = <replace with your path>/testdev2017.txt names = data/coco.names backup = backup eval=coco ``` 5. Create `/results/` folder near with `./darknet` executable file 6. Run validation: `./darknet detector valid cfg/coco.data cfg/yolov4.cfg yolov4.weights` 7. Rename the file `/results/coco_results.json` to `detections_test-dev2017_yolov4_results.json` and compress it to `detections_test-dev2017_yolov4_results.zip` 8. Submit file `detections_test-dev2017_yolov4_results.zip` to the MS COCO evaluation server for the `test-dev2019 (bbox)` #### How to evaluate FPS of YOLOv4 on GPU 1. Compile Darknet with `GPU=1 CUDNN=1 CUDNN_HALF=1 OPENCV=1` in the `Makefile` (or use the same settings with Cmake) 2. Download `yolov4.weights` file: https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT 3. Get any .avi/.mp4 video file (preferably not more than 1920x1080 to avoid bottlenecks in CPU performance) 4. Run one of two commands and look at the AVG FPS: * include video_capturing + NMS + drawing_bboxes: `./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -dont_show -ext_output` * exclude video_capturing + NMS + drawing_bboxes: `./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -benchmark` #### Pre-trained models There are weights-file for different cfg-files (trained for MS COCO dataset): FPS on RTX 2070 (R) and Tesla V100 (V): * [yolov4.cfg](https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4.cfg) - 245 MB: [yolov4.weights](https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT) paper [Yolo v4](https://arxiv.org/abs/2004.10934) * `width=608 height=608` in cfg: **65.7% mAP@0.5 (43.5% AP@0.5:0.95) - 34(R) FPS / 62(V) FPS** - 128.5 BFlops * `width=512 height=512` in cfg: **64.9% mAP@0.5 (43.0% AP@0.5:0.95) - 45(R) FPS / 83(V) FPS** - 91.1 BFlops * `width=416 height=416` in cfg: **62.8% mAP@0.5 (41.2% AP@0.5:0.95) - 55(R) FPS / 96(V) FPS** - 60.1 BFlops * `width=320 height=320` in cfg: **60% mAP@0.5 ( 38% AP@0.5:0.95) - 63(R) FPS / 123(V) FPS** - 35.5 BFlops * [yolov3-tiny-prn.cfg](https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov3-tiny-prn.cfg) - **33.1% mAP@0.5 - 370(R) FPS** - 3.5 BFlops - 18.8 MB: [yolov3-tiny-prn.weights](https://drive.google.com/file/d/18yYZWyKbo4XSDVyztmsEcF9B_6bxrhUY/view?usp=sharing) * [enet-coco.cfg (EfficientNetB0-Yolov3)](https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/enet-coco.cfg) - **45.5% mAP@0.5 - 55(R) FPS** - 3.7 BFlops - 18.3 MB: [enetb0-coco_final.weights](https://drive.google.com/file/d/1FlHeQjWEQVJt0ay1PVsiuuMzmtNyv36m/view) * [yolov3-openimages.cfg](https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov3-openimages.cfg) - 247 MB - 18(R) FPS - OpenImages dataset: [yolov3-openimages.weights](https://pjreddie.com/media/files/yolov3-openimages.weights) <details><summary><b>CLICK ME</b> - Yolo v3 models</summary> * [csresnext50-panet-spp-original-optimal.cfg](https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/csresnext50-panet-spp-original-optimal.cfg) - **65.4% mAP@0.5 (43.2% AP@0.5:0.95) - 32(R) FPS** - 100.5 BFlops - 217 MB: [csresnext50-panet-spp-original-optimal_final.weights](https://drive.google.com/open?id=1_NnfVgj0EDtb_WLNoXV8Mo7WKgwdYZCc) * [yolov3-spp.cfg](https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov3-spp.cfg) - **60.6% mAP@0.5 - 38(R) FPS** - 141.5 BFlops - 240 MB: [yolov3-spp.weights](https://pjreddie.com/media/files/yol