About the smooth the resulting class weights

[huixiancheng]

Hi, dear sir. Look like the weight of each class of your code is not same to rangenet++. https://github.com/Shathe/3D-MiniNet/blob/21a27838f3a43b3722406ed5a91fdef512f54910/pytorch_code/lidar-bonnetal/train/tasks/semantic/modules/trainer.py#L78-L81 Have your results show that the smooth weight is much better? Since there is not have a ablation study. Looking forward to your reply