ScaledYOLOv4 VS darknet

WongKinYiu/ScaledYOLOv4

I'm using a branch of the author's PyTorch repo

Take a look at yolov5 or scaled yolov4. They should both handle real-time training, at low enough resolution anyway; I don't know if there is any model that can do real-time detection on 4K videos. Don't pay attention to the version numbers, I think the scaled yolov4 is sliiiightly better performance.

[CVPR'21 WAD] Challenge - Waymo Open Dataset: https://waymo.com/open/challenges/2021/real-time-2d-prediction/ YOLOR (Scaled-YOLOv4-based) has the best speed/accuracy ratio on Waymo autonomous driving challenge ((Waymo Open Dataset): Real-time 2D Detection. Thanks Chien-Yao Wang from Academia Sinica and DiDi MapVision team to push Scaled-YOLOv4 further! * DIDI MapVision: https://arxiv.org/abs/2106.08713 * YOLOR https://arxiv.org/abs/2105.04206 * YOLOR-code (Pytorch): https://github.com/WongKinYiu/yolor * Scaled-YOLOv4(CVPR21): https://openaccess.thecvf.com/content/CVPR2021/html/Wang\_Scaled-YOLOv4\_Scaling\_Cross\_Stage\_Partial\_Network\_CVPR\_2021\_paper.html * Scaled-YOLOv4-code (Pytorch): https://github.com/WongKinYiu/ScaledYOLOv4 * YOLOv4: https://arxiv.org/abs/2004.10934 * YOLOv4-code (Darknet, Pytorch, TensorFlow, TRT, OpenCV…): https://github.com/AlexeyAB/darknet#yolo-v4-in-other-frameworks

The DiDi MapVision team has shown excellent results with the YOLOR and DIDI MapVision models, both based on Scaled-YOLOv4: * DIDI MapVision: https://arxiv.org/abs/2106.08713 * YOLOR https://arxiv.org/abs/2105.04206 * YOLOR-code (Pytorch): https://github.com/WongKinYiu/yolor * Scaled-YOLOv4(CVPR21): https://openaccess.thecvf.com/content/CVPR2021/html/Wang_Scaled-YOLOv4_Scaling_Cross_Stage_Partial_Network_CVPR_2021_paper.html * Scaled-YOLOv4-code (Pytorch): https://github.com/WongKinYiu/ScaledYOLOv4 * YOLOv4: https://arxiv.org/abs/2004.10934 * YOLOv4-code (Darknet, Pytorch, TensorFlow, TRT, OpenCV...): https://github.com/AlexeyAB/darknet#yolo-v4-in-other-frameworks

* Scaled-YOLOv4-code (Pytorch): https://github.com/WongKinYiu/ScaledYOLOv4

As for the BEST model, I would suggest you use Scaled YOLOv4 since it performs the best both on the cloud and edge devices.

You're out of sync, yolo-v5 is a controversial naming. And whatever side of the debate you are in state-of-the art is Scaled-Yolo v4: https://github.com/WongKinYiu/ScaledYOLOv4 https://arxiv.org/abs/2011.08036

To complicate matters further, the code for this improvement of YOLOv4 (published by one of the original YOLOv4 authors) is actually a fork of the YOLOv5 repo: https://github.com/WongKinYiu/ScaledYOLOv4/tree/yolov4-csp

YoloV3/4 is C based if that counts: https://github.com/AlexeyAB/darknet

This is all well-known information, see any (and all!) previous discussions when YOLOv5 comes up. For details: https://github.com/AlexeyAB/darknet/issues/5920

2) YOLOv5 is both slower and less precise than YOLOv4. Why use YOLOv5? Source: https://github.com/AlexeyAB/darknet/issues/5920

So my recommendation is you stuck with Darknet/YOLO and use v4 of YOLO. The Darknet framework license is definitely suitable for commercial use: https://github.com/AlexeyAB/darknet/blob/master/LICENSE

Still to long. Here's my favourite license: https://github.com/AlexeyAB/darknet/blob/master/LICENSE

When YOLOv7 was out, I built a web app to test it against the classic YOLOv4 and shared it with my team, then deployed it online to share with the community.

If you're worried about performance, you shouldn't be using YOLOv5 since it is slower (and less accurate!) than YOLOv4. Source: https://github.com/AlexeyAB/darknet/issues/5920

I looked around online but I only found this post discussing a related issue, leading me to think there seems to be some sort of compatibility issue going on here. And I think this is the most recent version of the file I am trying to compile located on the exact same folder where my copy is and when I opened it it shows CUDA 11.1 in line 307.