search

edwardzhou130 / PolarSeg

Implementation for PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020)
BSD 3-Clause "New" or "Revised" License
376 stars 80 forks source link

Label encoding #29

Closed abhigoku10 closed 3 years ago

abhigoku10 commented 3 years ago

@YangZhang4065 @Xyouz thanks for sharing the source code , can you please let me know what is the use of functions like " SemKITTI2train_single(label):" and "SemKITTI2train(label):" which is used during training and testing , how Is it modifying the labels during saving

Xyouz commented 3 years ago

Before calling the SemKitti2train function labels range from 0 (which represents points to be ignored) to 25 or so. The SemKitti2train function shift them by 1 so that they range from 0 to 24 (for the useful classes) and points that are to be ignored get labelled as 255.

abhigoku10 commented 3 years ago

@Xyouz for visualization on the nuscenes data what code base should be used ?

Xyouz commented 3 years ago

I won't be able to help you on this one as I only worked with the semantickitti data.