pytorch-auto-drive icon indicating copy to clipboard operation
pytorch-auto-drive copied to clipboard

Published 20 hours ago • verified publisher icon voldemortX

Trying to convert bezierlanenet to onnx

Open farouk09 opened this issue 3 years ago • 3 comments

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

farouk09 avatar Jun 01 '22 09:06 farouk09

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 avatar Jun 01 '22 10:06 voldemortX

@farouk09 I will list this as feature request.

voldemortX avatar Jun 01 '22 10:06 voldemortX

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

voldemortX avatar Jun 04 '22 04:06 voldemortX