Yolov5: Is there any plan to support RegNet?

[AlphaGoMK]

❔Question

Are you going to support training RegNet as backbone?

Additional context

[github-actions[bot]]

Hello @AlphaGoMK, 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 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.

[jinfagang]

@AlphaGoMK Does there any benifits for Regnet ?

[AlphaGoMK]

@AlphaGoMK Does there any benifits for Regnet ?

As mentioned in the paper, regnet outperform efficientnet on both top1 error and FLOPS.
But Im not sure whether it will work on object detection task or not.

[Aktcob]

outperform on top1 does not mean outperform on Detection task

[AlphaGoMK]

outperform on top1 does not mean outperform on Detection task

Agree.
Im not sure about its effectiveness on detection task cuz the paper did not contain any results on coco dataset, that's why I opened this issue :)

[glenn-jocher]

It can be a long journey from a classification to detection, as you can see in the differences (and time elapsed) between the releases of efficientnet and efficientdet.