Viet-Anh NGUYEN (Andrew)

@KroitAax Check this code for converting and loading model separately: https://github.com/vietanhdev/samexporter I will integrate it into the tool next week.

I also use Mac M1. Which release did you use? Have you tried [AnyLabeling.dmg](https://github.com/vietanhdev/anylabeling/releases/download/v0.3.3/AnyLabeling.dmg)?

I will look into .dmg version. In the meantime, you can use the Python version instead.

Thank you for your feedback! The issue will be solved in the next version.

Do you use the same version of YOLO here? https://anylabeling.nrl.ai/docs/custom-models

The YOLOV8 polygons are not supported at the moment. Thank you for your interest.

Please check the version of CUDA and CUDNN: - CUDA must be 11.6. - CUDNN: 8.2.4 (Linux), 8.5.0.96 (Windows). More information: [https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html).

Thank you for your suggestion.

Hi All, Please try Python 3.8 with the CPU version. ONNX and ONNXRuntime will be updated in the next version. Thank you.

Please provide us more info: - Images which cause this issue. - The steps to reproduce.