error for test seg task

[Excutioner]

During run torchpack dist-run -np 1 python tools/test.py configs/nuscenes/seg/fusion-bev256d2-lss.yaml pretrained/bevfusion-seg.pth --eval map I had the same problem as #461at first, but I added the following code after line 185 in nusences_converter.py file location = nusc.get( "log", nusc.get("scene", sample["scene_token"])["log_token"] )["location"] And added location to the info 'location': location, Rerun nusecenes_converter to regenerate the PKL file, the following error was encountered AttributeError: 'dict' object has no attribute 'in_range_bev'

[Yunge6666]

Have you solved this problem? I have the same problem...

[Qizhi697]

I have also got this problem during run torchpack dist-run -np 1 python tools/test.py configs/nuscenes/seg/fusion-bev256d2-lss.yaml pretrained/bevfusion-seg.pth --eval map. I don't know how to evaluate the pretrained model for the segmentation variant of BEVFusion. @zhijian-liu do you have any suggestions?

[zhijian-liu]

Thank you for your interest in our project. This repository is no longer actively maintained, so we will be closing this issue. Please refer to the amazing implementation at MMDetection3D. Thank you again!