-
-
Notifications
You must be signed in to change notification settings - Fork 15.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Some Questions about default Regression Loss Implementations #1113
Comments
Hello @cydiachen, 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:
For more information please visit https://www.ultralytics.com. |
@cydiachen yes you are correct. See #762 for a TODO on this. In terms of box regression metrics CIoU may perform slightly better on custom datasets per user feedback. |
Thx, Your reply cleared up my doubt. Thank you for your reply. |
@cydiachen I've opened PR #1120 to address this. Please review and comment there. |
❔Question
Thank you for the excellent job of yolov5. I have read your code and inspired a lot. However, I found that it is confusing that the regression loss in your code. In ./utils/general.py, you kindly provided three types of iou loss for us. But i Find that inside compute_loss function, you use bbox_iou() with CIoU= True, but you annotated this line as giou. It is really confusing for us to understand. Would you mind telling me the real configurations or the reason you choose CIoU mode of bbox_iou() for giou? THX a lot.
Additional context
The text was updated successfully, but these errors were encountered: