LukeAI

I found that exporting seems to work ok if I use the pretraining weights provided by https://github.com/Turoad/clrnet but if I train my own network, I get this error, with both...

OK I got this working literally just by deleting the offending dict keys: ``` del new_state_dict["heads.sample_x_indexs"] del new_state_dict["heads.prior_feat_ys"] del new_state_dict["heads.prior_ys"] del new_state_dict["heads.criterion.weight ``` inserted just before https://github.com/xuanandsix/CLRNet-onnxruntime-and-tensorrt-demo/blob/07a47e666d4bfca9a4c60a777c62c23828fca663/torch2onnx.py#L28 Edit. probably better...

@hkingtswcbyy any joy?

I'd also like to get this feature, but it looks like there's no active development happening here anymore, could be worth considering PRing to https://github.com/MaxandreOgeret/vcstool2/

> Hi @LukeAI, > > I don't currently plan putting more effort in this PR. Do feel free however to port this to the new vcstool2 repo. ;) fair enough!...