2

I used this repo : https://github.com/Turoad/lanedet to convert a pytorch model that use mobilenetv2 as backbone To ONNX but I didn't succeeded.

i got a Runtime error that says:

RuntimeError: Exporting the operator eye to ONNX opset version 12 is not supported. Please open a bug to request ONNX export support for the missing operator.

it's really disappointing, looking to the good result that this model gives and the quick performance that it provides,

is there any way that I can fix this bug? because I need to convert it to ONNX and then to TF lite model to use it in Android App I will provide the pretrained model that I have used and the way that I follow in converting..

Thank you so much for helping!

my colab notebook:

https://colab.research.google.com/drive/18udIh8tNJvti7jKmR4jRaRO-oYDgRmvA?usp=sharing

the pretrained model that I use:

https://drive.google.com/file/d/1o3-BgLIQesurIyDCKGliqbo2inUA5cPw/view?usp=sharing

Abdul Hakawati
  • 23
  • 4
  • Welcome to stackoverflow: users might downvote or ignore the question in its current format. Please see how to ask questions: https://stackoverflow.com/help/minimal-reproducible-example – D.L Mar 13 '22 at 10:28

1 Answers1

0

Use torch>=1.7.0 to convert the model, because operation Eye is added.

teplandr
  • 176
  • 1
  • 9
  • Thanks! it worked when I used the latest version available on colab but I got a cuda runtime error sadly! – Abdul Hakawati Mar 15 '22 at 11:19
  • > RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. – Abdul Hakawati Mar 15 '22 at 11:20