onnx2torch
onnx2torch copied to clipboard
require to support operator 'ArgMax'
Met the following error, hope to support operator 'ArgMax', thanks
Traceback (most recent call last):
File "anna_onnx2torch.py", line 38, in
Hey @Lin-Tao-AI ,
I'm already developing this operator. Actually I'm having some problems, but I think I should solve it soon.
I think we will support it soon.
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 10 days.
This issue was closed because it has been stalled for 10 days with no activity.
Is there any progress on this? I'm facing this issue in trying to round trip a torch model => onnx and then back to torch.
onnx2torch == 1.5.7
If it would help, I can share my model file also.
Implemented: https://github.com/ENOT-AutoDL/onnx2torch/releases/tag/v1.5.15