Albumentations in yolov8-obb (8.1.1)

ultralytics / ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

https://docs.ultralytics.com

GNU Affero General Public License v3.0

28.92k stars 5.72k forks source link

Albumentations in yolov8-obb (8.1.1) #7672

Closed rkinas closed 7 months ago

rkinas commented 8 months ago

Search before asking

[X] I have searched the YOLOv8 issues and found no similar bug report.

YOLOv8 Component

Augmentation

Bug

Albumentations geometrical transformation (e.g. RandomRotate90) do not work. in Albumentations Yolo box tansformation format is implemented which is different from OBB. As a result, boxes are not transferred correctly.

self.transform = A.Compose(T, bbox_params=A.BboxParams(format="yolo", label_fields=["class_labels"]))

I realize that this is an external library, but I am letting you know in order to introduce information in the documentation that this kind of augmentation will not function properly.

Environment

No response

Minimal Reproducible Example

No response

Additional

No response

Are you willing to submit a PR?

[ ] Yes I'd like to help by submitting a PR!

glenn-jocher commented 8 months ago

@rkinas thank you for bringing this to our attention. We acknowledge the issue with Albumentations' geometrical transformations not correctly handling the OBB format in YOLOv8-obb. We appreciate your suggestion and will consider updating our documentation to reflect this limitation. Your input is valuable to the community, and we aim to provide the most accurate information possible. If you have further insights or suggestions, please feel free to share. 📚🛠️

github-actions[bot] commented 7 months ago

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

Docs: https://docs.ultralytics.com
HUB: https://hub.ultralytics.com
Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐