Zhengyang Feng

Yes they are untested. As I remember, our accuracy seems to match LaneATT but FP and FN seems off. Maybe @cedricgsh can provide some further details about LaneATT.

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.

@farouk09 I will list this as feature request.

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

@sjtuljw520 I will check if this is supported, but perhaps tomorrow, I don't have the test environment now.

@sjtuljw520 The development of LaneATT seems to have deviated from the main branch for a long time (quote @cedricgsh), so it was untested on conversions. I will mark this as...

@sjtuljw520 if you download anchors from LaneATT repo and use opset 11, torch 1.8 (and corresponding mmcv), the model can be converted to onnx. But not trt yet. I'm working...

> So if the NMS op is included in the model, the conversion can not work and will enconter error? @voldemortX Yes. It is a customized cuda kernel, which is...

But it looks like an op that is suitable to be included in customized post-processing impl, such as a customized SDK function or something.

@sjtuljw520 With 4419bba & #102, you should be able to convert LaneATT to ONNX and TensorRT (check the new doc, you will need pytorch 1.8.0 & nvidia-tensorrt 8.4.1.5). _Except for...