YOLOv10 to onnx format

[shimaamorsy]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

How to export yolov10-seg to onnx format ?

Additional

No response

[glenn-jocher]

@shimaamorsy hello!

Thank you for reaching out with your question on exporting YOLOv10-seg to ONNX format. While YOLOv10 isn't officially released by Ultralytics, I can guide you on how to export a YOLOv5 model to ONNX, which should be similar for any future versions.

First, ensure you have the latest version of the YOLOv5 repository and the required dependencies:

git clone https://github.com/ultralytics/yolov5
cd yolov5
pip install -r requirements.txt

To export a YOLOv5 model to ONNX format, you can use the export.py script. Here's an example command:

python export.py --weights yolov5s.pt --include onnx

Replace yolov5s.pt with the path to your trained YOLOv10-seg model weights. This command will generate an ONNX file in the same directory.

For more detailed instructions, you can refer to our Model Export Tutorial.

If you encounter any issues during the export process, please provide a minimum reproducible example so we can assist you better. You can find guidance on creating one here.

Feel free to reach out if you have any further questions. Happy coding! 🚀

[github-actions]

👋 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 ⭐

[rlewkowicz]

Bro whos thumbs downing glenn!? Yall, do you even understand the brilliance that goes into this stuff? Sorry you can't copy paste some of the most cutting edge technical work on the planet. The thumbs down makes me mad actually. The entitlement. Go ask on the yolov10 repo my people.

[glenn-jocher]

Hello @rlewkowicz,

Thank you for your supportive words and enthusiasm for the work being done here! The YOLO community and the Ultralytics team truly appreciate it. 😊

Regarding your earlier question about exporting YOLOv10-seg to ONNX format, I provided some steps and guidance on how to achieve this using the current YOLOv5 framework. If you have any specific issues or further questions, feel free to share them here, and I'll be happy to assist you.

For anyone experiencing issues or bugs, I encourage you to ensure that you are using the latest versions of the packages and the repository. This often resolves many common problems.

If you have any other questions or need further assistance, please don't hesitate to ask. We're here to help!

[GabrieldeBlois]

Hi, I would like to do QAT for yolov10. I couldn't find the proper documentation. Can you guide me ?

[glenn-jocher]

Hello @GabrieldeBlois,

Currently, we don't have specific documentation for QAT (Quantization Aware Training) for YOLOv10. However, you can refer to the general QAT guidelines available for YOLOv5 and adapt them accordingly. If you encounter specific issues, feel free to ask here.