Bhushan Sonawane

this should be fixed in latest aimet could you please check with latest aimet-torch https://pypi.org/project/aimet-torch/?

Hi @tholmb aimet tensorflow is in maintance mode and will not get any new features. Please use https://pypi.org/project/aimet-torch/ and https://pypi.org/project/aimet-onnx for your latest workflow. Or use https://github.com/quic/aimet/releases for latest aimet-tensorflow...

@Eman-Su please give a try with our latest release https://pypi.org/project/aimet-torch/ https://pypi.org/project/aimet-onnx please re-open this issue if this still persists. Closing due to inactivity.

Hi @superpigforever please do not use `--input_list` option along with aimet quantized model as this option triggers quantization in converter which will use provided input to fill in the missing...

Hi @jianbin-zhang now we have much better release and installation process. Please try installing aimet form pypi from here https://pypi.org/project/aimet-torch/ You can install onnx from https://pypi.org/project/aimet-onnx/

Thanks @pei0033 for detailed issue and repro script. Will run this internally and get back to you with initial feedback.

Hi @e-said now we can install aimet with pip package with this issue is no longer relevant. closing out. Please re-open if you have issues with latest aimet and torch...

@zhihaofan could you please share an example that you have to repro this issue? also, would be great if you can try with our latest aimet-torch https://pypi.org/project/aimet-torch/

Hi @TingfengTang as @RangineniBalaji mentioned, this is indeed torch fx issue. Coudl you please try with the latest torch if this still persists.

Hi @Jamil as @e-said mentioned, this seems to be torch fx issue. torch fx cannot handle branches that are present in Yolo model. In this case, you can skip model_preparer...