Will you add yolov4 support

[intgogo]

This repo has very good training skills. And most important of all,this repo can support export-onnx model and onnx is really good for production deployment.

[github-actions]

Hello @intgogo, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@intgogo yes, a yolov4 yaml file would be a good addition. We are extremely busy, however if you'd like to help create one we would welcome the PR!

[Lornatang]

@intgogo @glenn-jocher Try it? Pull requests #153.

[glenn-jocher]

@Lornatang thanks for the PR! I looked it over, it's a good try, but I believe the yolov4 architecture there is not quite correct. The head specifically should be a PANet head.

Implementing it exactly correctly will be a challenge. The best guide is the existing darknet cfg files like this one, that you can visualize with Netron.
https://github.com/ultralytics/yolov3/blob/master/cfg/yolov4.cfg

[Lornatang]

@glenn-jocher In the original YOLOv4, its activation function is Mish, and here I am LeakyReLU. I quickly tested a real data set, and the results are very satisfying to me. #6

It'is YOLOv5l result:

It'is YOLOv4 result:

[arthurfortes]

@glenn-jocher In the original YOLOv4, its activation function is Mish, and here I am LeakyReLU. I quickly tested a real data set, and the results are very satisfying to me. #6

It'is YOLOv5l result:

It'is YOLOv4 result:

Could you share the yolo v4 weights in .pt?

[Lornatang]

@arthurfortes Not yet, I have not obtained permission.emm...

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.