[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-6026":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},6026,"darknet","pjreddie\u002Fdarknet","pjreddie","Convolutional Neural Networks","http:\u002F\u002Fpjreddie.com\u002Fdarknet\u002F",null,"C",26461,21074,894,1811,0,3,8,19,9,45,"Other",false,"master",true,[],"2026-06-12 02:01:15","![Darknet Logo](http:\u002F\u002Fpjreddie.com\u002Fmedia\u002Ffiles\u002Fdarknet-black-small.png)\n\n# Darknet #\nDarknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.\n\n**Discord** invite link for for communication and questions: https:\u002F\u002Fdiscord.gg\u002FzSq8rtW\n\n## YOLOv7: \n\n* **paper** - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors: https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.02696\n\n* **source code - Pytorch (use to reproduce results):** https:\u002F\u002Fgithub.com\u002FWongKinYiu\u002Fyolov7\n\n----\n\nOfficial YOLOv7 is more accurate and faster than YOLOv5 by **120%** FPS, than YOLOX by **180%** FPS, than Dual-Swin-T by **1200%** FPS, than ConvNext by **550%** FPS, than SWIN-L by **500%** FPS.\n\nYOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100, batch=1.\n\n* YOLOv7-e6 (55.9% AP, 56 FPS V100 b=1) by `+500%` FPS faster than SWIN-L Cascade-Mask R-CNN (53.9% AP, 9.2 FPS A100 b=1)\n* YOLOv7-e6 (55.9% AP, 56 FPS V100 b=1) by `+550%` FPS faster than ConvNeXt-XL C-M-RCNN (55.2% AP, 8.6 FPS A100 b=1)\n* YOLOv7-w6 (54.6% AP, 84 FPS V100 b=1) by `+120%` FPS faster than YOLOv5-X6-r6.1 (55.0% AP, 38 FPS V100 b=1)\n* YOLOv7-w6 (54.6% AP, 84 FPS V100 b=1) by `+1200%` FPS faster than Dual-Swin-T C-M-RCNN (53.6% AP, 6.5 FPS V100 b=1)\n* YOLOv7x (52.9% AP, 114 FPS V100 b=1) by `+150%` FPS faster than PPYOLOE-X (51.9% AP, 45 FPS V100 b=1)\n* YOLOv7 (51.2% AP, 161 FPS V100 b=1) by `+180%` FPS faster than YOLOX-X (51.1% AP, 58 FPS V100 b=1)\n\n----\n\n![more5](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F179425274-f55a36d4-8450-4471-816b-8c105841effd.jpg)\n\n----\n\n![image](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F177675030-a929ee00-0eba-4d93-95c2-225231d0fd61.png)\n\n\n----\n\n![yolov7_640_1280](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F177688869-d75e0c36-63af-46ec-bdbd-81dbb281f257.png)\n\n----\n\n## Scaled-YOLOv4: \n\n* **paper (CVPR 2021)**: https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fhtml\u002FWang_Scaled-YOLOv4_Scaling_Cross_Stage_Partial_Network_CVPR_2021_paper.html\n\n* **source code - Pytorch (use to reproduce results):** https:\u002F\u002Fgithub.com\u002FWongKinYiu\u002FScaledYOLOv4\n\n* **source code - Darknet:** https:\u002F\u002Fgithub.com\u002FAlexeyAB\u002Fdarknet\n\n* **Medium:** https:\u002F\u002Falexeyab84.medium.com\u002Fscaled-yolo-v4-is-the-best-neural-network-for-object-detection-on-ms-coco-dataset-39dfa22fa982?source=friends_link&sk=c8553bfed861b1a7932f739d26f487c8\n\n## YOLOv4:\n\n* **paper:** https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.10934\n\n* **source code:** https:\u002F\u002Fgithub.com\u002FAlexeyAB\u002Fdarknet\n\n* **Wiki:** https:\u002F\u002Fgithub.com\u002FAlexeyAB\u002Fdarknet\u002Fwiki\n\n* **useful links:** https:\u002F\u002Fmedium.com\u002F@alexeyab84\u002Fyolov4-the-most-accurate-real-time-neural-network-on-ms-coco-dataset-73adfd3602fe?source=friends_link&sk=6039748846bbcf1d960c3061542591d7\n\nFor more information see the [Darknet project website](http:\u002F\u002Fpjreddie.com\u002Fdarknet).\n\n\n\u003Cdetails>\u003Csummary> \u003Cb>Expand\u003C\u002Fb> \u003C\u002Fsummary>\n\n![yolo_progress](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F146988929-1ed0cbec-1e01-4ad0-b42c-808dcef32994.png) https:\u002F\u002Fpaperswithcode.com\u002Fsota\u002Fobject-detection-on-coco\n\n----\n\n![scaled_yolov4](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F112776361-281d8380-9048-11eb-8083-8728b12dcd55.png) AP50:95 - FPS (Tesla V100) Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.08036\n\n----\n\n![YOLOv4Tiny](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F101363015-e5c21200-38b1-11eb-986f-b3e516e05977.png)\n\n----\n\n![YOLOv4](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F90338826-06114c80-dff5-11ea-9ba2-8eb63a7409b3.png)\n\n\u003C\u002Fdetails>\n\n----\n\n![OpenCV_TRT](https:\u002F\u002Fuser-images.githubusercontent.com\u002F4096485\u002F90338805-e5e18d80-dff4-11ea-8a68-5710956256ff.png)\n\n\n## Citation\n\n\n```\n@misc{https:\u002F\u002Fdoi.org\u002F10.48550\u002Farxiv.2207.02696,\n  doi = {10.48550\u002FARXIV.2207.02696},\n  url = {https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.02696},\n  author = {Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},\n  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},\n  title = {YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},\n  publisher = {arXiv},\n  year = {2022}, \n  copyright = {arXiv.org perpetual, non-exclusive license}\n}\n```\n\n```\n@misc{bochkovskiy2020yolov4,\n      title={YOLOv4: Optimal Speed and Accuracy of Object Detection}, \n      author={Alexey Bochkovskiy and Chien-Yao Wang and Hong-Yuan Mark Liao},\n      year={2020},\n      eprint={2004.10934},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n\n```\n@InProceedings{Wang_2021_CVPR,\n    author    = {Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},\n    title     = {{Scaled-YOLOv4}: Scaling Cross Stage Partial Network},\n    booktitle = {Proceedings of the IEEE\u002FCVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n    month     = {June},\n    year      = {2021},\n    pages     = {13029-13038}\n}\n```\n","Darknet 是一个用 C 和 CUDA 编写的开源神经网络框架，支持 CPU 和 GPU 计算。它以高效、易于安装著称，并且在物体检测领域表现出色，特别是 YOLOv7 版本，在速度和精度上均超越了包括 YOLOv5、YOLOX 在内的其他知名实时物体检测器。例如，YOLOv7 在 NVIDIA V100 GPU 上运行时比 SWIN-L 快 500%，同时保持更高的精度（56.8% AP）。Darknet 适合需要高性能图像处理的应用场景，如自动驾驶、安防监控以及任何对实时性要求较高的视觉分析任务。",2,"2026-06-11 03:05:24","top_language"]