Giters

ultralytics / hub

Ultralytics HUB tutorials and support

Home Page:https://hub.ultralytics.com

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

OBB Labels direct from Segmentation Labels

jquaglia-uss opened this issue · comments

commented

Search before asking

  • I have searched the HUB issues and found no similar feature requests.

Description

Hello Ultralytics Team! I think a useful feature would be to have the ability to train a OBB detect model directly from Segmentation labels. I know I could write a script to convert my segmentation polygons to OBB format and then kick off a train, but I think it would really help accelerate OBB detect trainings if it was integrated into a train step. This way if there are hundreds of users out there with segmentation labels, they don't individually need to make and run this script, they could just feed in the polygon labels and the API would realize the labels are polygon and generate a best fix OBB before training. OR this could be during upload to HUB? Not a hugely important feature, but it would centralize the conversion, saving time for users.

Use case

No response

Additional

No response

commented

@jquaglia-uss hello! Thank you for your feature request and for taking the time to check the existing issues before posting. 🌟

The idea of integrating the conversion of segmentation labels to oriented bounding box (OBB) labels directly into the training pipeline or during the upload to the HUB is indeed an interesting one. It could streamline the process for users who have segmentation data and are looking to train an OBB detection model.

We appreciate your suggestion as it highlights a potential area for enhancing user experience and efficiency. I'll bring this to the attention of our team for consideration in future updates. Meanwhile, if you have any further insights or specific requirements for this feature, please feel free to share them with us.

Your input is valuable, and we're committed to improving the HUB based on the feedback and needs of our community. Keep the great ideas coming! 😊

For any further questions or discussions, please refer to our documentation at https://docs.ultralytics.com/hub.

commented

👋 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:

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 ⭐

commented

closing this out here... that is in fact how it already works! smh...

commented

@jamesquags, no worries at all! It's great to hear that the functionality you were looking for is already in place. 😄 Sometimes features can be overlooked, so it's always worth asking.

If you have any more questions or if there's anything else you'd like to explore, feel free to reach out. We're here to help. Happy training, and thank you for being a part of the YOLO community and using the Ultralytics HUB! 🚀

commented

👋 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:

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 ⭐