Lue Fan

Please open a new issue. Otherwise, I may forget to answer your question when I am free. Thanks! @atlantins

We normalize intensity here: https://github.com/tusen-ai/SST/blob/main/mmdet3d/models/detectors/single_stage_fsd.py#L287 Sorry for the hard coding. I suggest training a model without intensity, only taking xyz as input. Otherwise, even if you normalize the intensity to...

It should not be so. I provide complete training logs in the URLs in the instructions. I suggest that first compare your log with the provided logs to debug.

What I mean is to compare the training log (not only the config) and see if there are any significant differences (e.g., losses and other printed items). Besides, could you...

Thanks for your feedback. It seems that the training goes well but there are errors during the inference. Have you made **any** modifications to this repo?

In addition, is your validation data complete? How many samples are found by the WOD evaluation bool (the printed number during evaluation)?

You could try our pretrained model in nuScenes to see if Waymo data corrupts.

What do you mean by `accuracy dropped`? Worse than the base detector? FSDv2 does not adopt roi_head in nusc is because the metric in nusc is center-based instead of IoU-based,...

@JuiceLemonLemon

@yrt1993 We tested our checkpoint again, and the performance can be perfectly reproduced.