lqzhao

core dumped problem

2

Hi, thanks for your selfless code sharing. I encountered the following error when I run python -m pointnet2.train.train_cls. {'batch_size': 16, 'bn_momentum': 0.5, 'bnm_decay': 0.5, 'checkpoint': None, 'decay_step': 200000.0, 'epochs': 200,...

Can't reproduce the performance on the ScanNet dataest.

1

Hi, I tried to train the model on the ScanNet dataset, but we got a very worse result, compared with the result reported in the paper. We got 0.2440 on...

NYU performance

5

Hi Alex, Thanks for your great work. I'm reproducing the NYU v2 (generalization) experiments. I followed the instructions to prepare NYU data provided by you. When I used your pre-trained...

Pretrained models

4

Thanks for your great work! I'm trying to modify the architecture of KPConv and we cannot easily reproduce the performance mentioned in your paper because of the time constraint. So...

validating efficiency

1

Hi, thanks for your great work. I found the validating efficiency is not good because it will cost about 10 hours to test each image with 6 scales. I reduce...

incomplete codebase

1

Hi, great work! Lack requirements, dataset links, models