search

tsunghan-wu / RandLA-Net-pytorch

:four_leaf_clover: Pytorch Implementation of RandLA-Net (https://arxiv.org/abs/1911.11236)
MIT License
122 stars 33 forks source link

I have tried on the nuscense dataset. The results seem not well. #28

Open didiwei60 opened 1 year ago

didiwei60 commented 1 year ago

1 2 I have trained 30 epoches. The best accuracy and iou is only 33.75% and 23.16%, respectively. I have used 1800 samples in Nuscense dataset. Each sample contains 34000 points. The learning rate is set to 0.001. CosineAnnealingLR strategy is token.. I wonder if anything wrong with me. Thank you very much.