0

I'm exporting an ML model from PyTorch to ONNX model with torch.onnx.export function.

When I use PyTorch model, it has NVTX annotations for optimization which are used for Nsight system.

But when I changed the model from PyTorch to ONNX, it just went away.

How can I use NVTX in ONNX model?

I use model = onnx.load(onnx_file) for a function call, so I cannot annotate NVTX code snippets on the code itself.

Ryan
  • 73
  • 7
  • Could you share a reproducible example of the Pytorch code and of the ONNX code? So it can be more clear what you would like to annotate and profile. – Zois Tasoulas Sep 26 '22 at 20:36

0 Answers0