search

hustvl / MapTR

[ICLR'23 Spotlight] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
MIT License
982 stars 150 forks source link

export onnx error ( We don't have an op for aten::mul but it isn't a special case ) #136

Open zhaoxiaolong2020 opened 7 months ago

zhaoxiaolong2020 commented 7 months ago

when i export maptr to onnx ，report error as below : RuntimeError: 0INTERNAL ASSERT FAILED at "../torch/csrc/jit/ir/alias_analysis.cpp":584, please report a bug to PyTorch. We don't have an op for aten::mul but it isn't a special case. Argument types: Tensor, bool,

please help find which line cause this error , maybe op not support , and how to replace op to solve , thanks alot

LordonCN commented 6 months ago

Have you solved this problem now？ You can try to export maptr_tiny_r50_24e_bevformer.py model, which is nearly same to bevformer

xll426 commented 5 months ago

I met the same problem too

xll426 commented 5 months ago

Which operator is not supported? I found that there is deformable in the config of your model.

xll426 commented 5 months ago

I used maptr_nano_r18_110e.py to export onnx