I can convert ocrnet pytorch's model to onnx(tmp.onnx), however --verify shows that: outputs between tmp.onnx and pytorch model have big difference.

[lyf6]

Thanks for your error report and we appreciate it a lot.

Checklist

1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.

Describe the bug
A clear and concise description of what the bug is.

Reproduction

1. What command or script did you run?

   A placeholder for the command.
   

2. Did you make any modifications on the code or config? Did you understand what you have modified?

3. What dataset did you use?

Environment

1. Please run python mmseg/utils/collect_env.py to collect necessary environment infomation and paste it here.
2. You may add addition that may be helpful for locating the problem, such as
   • How you installed PyTorch [e.g., pip, conda, source]
   • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback

If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix

If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

[MengzhangLI]

Hi, @RunningLeon sorry for bothering again!

Could you please check out this issue when your time available? Thank you so much!

Best,

[RunningLeon]

@lyf6 Hi, sorry for the late reply. Could provide the full scripts ?

[skaldesh]

I experimented with the ONNX export quite a lot in the last days, and I have the same issue for example with Fast-SCNN and DeeplabV3Plus.
See #1044 for example