WongKinYiu/YOLO

Would you support conversion from torch to onnx and ncnn?

stereomatchingkiss opened this issue · 7 comments

stereomatchingkiss commented

As the title mentioned, one of the strength of yolov9 is the relatively high accuracy with smaller size and faster speed, a great tool for embedded devices. I think it would be a nice feature for this project

ramonhollands commented

@henrytsui000 I would like to contribute in this one. Is there any work done on exporting to different formats like onnx, coreml and tflite?

  • 👍1
henrytsui000 commented

@henrytsui000 I would like to contribute in this one. Is there any work done on exporting to different formats like onnx, coreml and tflite?

Thanks a lot!

You may find some existing code here:

YOLO/yolo/utils/deploy_utils.py

Line 11 in dc88787

class FastModelLoader:

To be honest, I'm not sure if the code is robust enough, but you can activate it using the following command:

python yolo/lazy.py task=inference task.fast_inference=onnx

Currently, it only supports ONNX and TensorRT.

If you're willing, you can add support for CoreML and TFLite, and help make the code more robust.

Best regards,
Henry Tsui

ramonhollands commented

Thanks for your reply. Gonna check and try to contribute on this next weeks!

ramonhollands commented

@henrytsui000
I think we want to remove the auxiliary branch on all export formats, right?

'''

if self.compiler == "onnx":
return self._load_onnx_model(device)
elif self.compiler == "trt":
return self._load_trt_model().to(device)
elif self.compiler == "deploy":
self.cfg.model.model.auxiliary = {}

'''

henrytsui000 commented

Yes, the auxiliary header is only used to train the model