RuntimeError: Exporting the operator grid_sampler to ONNX opset version 11 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub. about clrnet-onnxruntime-and-tensorrt-demo HOT 4 OPEN

In this code, import grid_sample op ( in clr_head.py line 21 and 126) to replace F.grid_sample (in clr_head.py line 123)
Specifically，please refer to the part of conver and test onnx,
3、cp clr_head.py (in this code) to your_path/CLRNet/clrnet/models/heads/
4、mkdir your_path/CLRNet/modules/ and cp grid_sample.py (in this code) to your_path/CLRNet/modules/

from clrnet-onnxruntime-and-tensorrt-demo.

Thanks @xuanandsix!

So, after this change I get this crash:-
#3

Do I need to retrain model with this new clr_head.py?

from clrnet-onnxruntime-and-tensorrt-demo.

No, this code is to help deploy the trained model from official code.

from clrnet-onnxruntime-and-tensorrt-demo.

Hi,"Have you solved the problem? After training using the original clr_head.py, I found that the size of the weights is different from the official weights. However, the trained weights can be used for inference normally, but when converting to onnx, I encountered the same error as you did. However, when I retrained using the new clr_head.py, I encountered the following error: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! Do you have any good suggestions? Thank you!"

from clrnet-onnxruntime-and-tensorrt-demo.