Exporting the operator 'aten::scaled_dot_product_attention' to ONNX opset version 17 is not supported.

[Albert337]

hi,first of all,thanks for sharing the project for us! but when i try to run the "export.py" code,i get the error
torch.onnx.errors.UnsupportedOperatorError: Exporting the operator 'aten::scaled_dot_product_attention' to ONNX opset version 17 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub: https://github.com/pytorch/pytorch/issues. i referred to the issue #19 and #32，and my environment is
WSL2 Ubuntu 22.04 Python 3.10.13 CUDA 11.8 CUDNN 8.9.4 TensorRT 8.6.1 numpy==1.24.1 onnxruntime-gpu==1.16.0 opencv-python==4.8.0.76 matplotlib==3.8.0, i tried to change opeset value,but it did not work.
is there any suggestions ?thanks

[fabio-sim]

Hi @Albert337, thank you for your interest in LightGlue-ONNX.

What's your PyTorch version? Version 2.1.0 is required. Please refer to requirements-export.txt:

LightGlue-ONNX/requirements-export.txt

Lines 1 to 8 in 85d7050

	# Freeze PyTorch versions to ensure consistent ONNX graph export for pattern matching
	torch==2.1.0
	torchvision==0.16.0
	onnx==1.14.1
	onnxruntime-gpu==1.16.0
	kornia==0.7.0
	opencv-python
	matplotlib

[Kanan99]

Can the model be exported using Torch version 2.1.0 and subsequently utilize the TRT engine on a different version of CUDA and Torch on the same device?

[fabio-sim]

Hi @Kanan99, thank you for your interest in LightGlue-ONNX.

Yes, that's the whole point of exporting to ONNX - platform interoperability - so that you can avoid having to install PyTorch as a dependency.