darknet/README.md

71 lines
2.6 KiB
Markdown
Raw Normal View History

2015-07-11 03:33:24 +03:00
![Darknet Logo](http://pjreddie.com/media/files/darknet-black-small.png)
2018-03-25 15:36:04 +03:00
# Darknet #
2015-07-11 03:33:24 +03:00
Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.
2020-11-24 20:18:20 +03:00
**Discord** invite link for for communication and questions: https://discord.gg/zSq8rtW
2020-12-07 17:37:07 +03:00
## Scaled-YOLOv4:
2021-08-22 02:50:36 +03:00
* **paper (CVPR 2021)**: https://openaccess.thecvf.com/content/CVPR2021/html/Wang_Scaled-YOLOv4_Scaling_Cross_Stage_Partial_Network_CVPR_2021_paper.html
2020-12-07 17:37:07 +03:00
2020-12-10 22:54:19 +03:00
* **source code - Pytorch (use to reproduce results):** https://github.com/WongKinYiu/ScaledYOLOv4
2020-12-07 17:37:07 +03:00
2020-12-08 13:16:39 +03:00
* **source code - Darknet:** https://github.com/AlexeyAB/darknet
2020-12-07 17:37:07 +03:00
2020-12-08 13:16:39 +03:00
* **Medium:** https://alexeyab84.medium.com/scaled-yolo-v4-is-the-best-neural-network-for-object-detection-on-ms-coco-dataset-39dfa22fa982?source=friends_link&sk=c8553bfed861b1a7932f739d26f487c8
2020-12-07 19:11:16 +03:00
2020-08-16 19:17:19 +03:00
## YOLOv4:
2020-04-24 04:15:09 +03:00
2020-08-16 19:17:19 +03:00
* **paper:** https://arxiv.org/abs/2004.10934
2020-04-24 04:15:09 +03:00
2020-08-16 19:17:19 +03:00
* **source code:** https://github.com/AlexeyAB/darknet
2020-07-19 23:56:14 +03:00
2020-08-16 19:17:19 +03:00
* **Wiki:** https://github.com/AlexeyAB/darknet/wiki
* **useful links:** https://medium.com/@alexeyab84/yolov4-the-most-accurate-real-time-neural-network-on-ms-coco-dataset-73adfd3602fe?source=friends_link&sk=6039748846bbcf1d960c3061542591d7
2020-06-02 14:44:57 +03:00
2015-07-11 03:33:24 +03:00
For more information see the [Darknet project website](http://pjreddie.com/darknet).
2015-08-06 02:56:24 +03:00
For questions or issues please use the [Google Group](https://groups.google.com/forum/#!forum/darknet).
2020-08-16 19:17:19 +03:00
2021-04-07 03:17:02 +03:00
![scaled_yolov4](https://user-images.githubusercontent.com/4096485/112776361-281d8380-9048-11eb-8083-8728b12dcd55.png) AP50:95 - FPS (Tesla V100) Paper: https://arxiv.org/abs/2011.08036
2020-12-07 17:37:07 +03:00
----
2020-08-16 19:17:19 +03:00
2020-12-07 17:37:07 +03:00
![YOLOv4Tiny](https://user-images.githubusercontent.com/4096485/101363015-e5c21200-38b1-11eb-986f-b3e516e05977.png)
2020-08-16 19:17:19 +03:00
----
![YOLOv4](https://user-images.githubusercontent.com/4096485/90338826-06114c80-dff5-11ea-9ba2-8eb63a7409b3.png)
----
![OpenCV_TRT](https://user-images.githubusercontent.com/4096485/90338805-e5e18d80-dff4-11ea-8a68-5710956256ff.png)
2021-07-08 01:13:20 +03:00
## Citation
```
@misc{bochkovskiy2020yolov4,
title={YOLOv4: Optimal Speed and Accuracy of Object Detection},
author={Alexey Bochkovskiy and Chien-Yao Wang and Hong-Yuan Mark Liao},
year={2020},
eprint={2004.10934},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
```
@InProceedings{Wang_2021_CVPR,
author = {Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
title = {{Scaled-YOLOv4}: Scaling Cross Stage Partial Network},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {13029-13038}
}
```