search

voldemortX / pytorch-auto-drive

PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help
BSD 3-Clause "New" or "Revised" License
837 stars 137 forks source link

Trying to convert bezierlanenet to onnx #97

Open farouk09 opened 2 years ago

farouk09 commented 2 years ago

Hi,

I'm trying to convert bezierlanenet to onnx, first i got this error:

RuntimeError: Exporting the operator flip to ONNX opset version 9 is not supported. Support for this operator was added in version 10, try exporting with this version.

I have changed the oppset version to 10 but now i'm getting this error, any helps !

RuntimeError: ArrayRef: invalid index Index = 2; Length = 2

voldemortX commented 2 years ago

I don't think it is supported yet (and I remember saying that in the documentation?), considering the deformable conv from mmcv. Although technically mmcv supports it in beta versions.

voldemortX commented 2 years ago

@farouk09 I will list this as feature request.

voldemortX commented 2 years ago

Perhaps we can do something like in here: https://github.com/shouxieai/tensorRT_Pro/tree/main/tutorial/2.0CenterNet_from_torch_trt