Pointnet_Pointnet2_pytorch
Pointnet_Pointnet2_pytorch copied to clipboard
yanx27
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
if the center point of block(1m*1m) is random chioce ?and how can you get it no-repeatly.Thank you very much!
Modify PSNet to be the project URL for the final paper, the previous URL was a temporary address prepared for the double-blind. Thank you very much for your contribution! Several...
I would appreciate it if you could give me some advice and help. My dataset is made in the form of s3dis. @yanx27 
您好，我仿照S3DIS数据集做了自己的数据样本，但是用您的代码跑语义分割，到了 ”for i, (points, target) in tqdm(enumerate(trainDataLoader), total=len(trainDataLoader), smoothing=0.9):“就跑不动。跑S3DIS数据集没有问题。谢谢
As mentioned in Line 12 of `collect_indoor3d_data.py`, the processed data is saved in `data/stanford_indoor3d` instead of `data/s3dis/stanford_indoor3d`
The processed data in case of Semantic Segmentation task is stored in `data/stanford_indoor3d` instead of `data/s3dis/stanford_indoor3d` (as per Line 12 in `data_utils/collect_indoor3d_data.py`).
Hi, thanks for your nice work. When I tested semantic segmentation, I reported an error and couldn't understand it. I hope I can get your help. Thank you in advance....
This error occurs when I execute the train_semseg.py: PS F:\pointnet_pointnet2_pytorch-master> python train_semseg.py --model pointnet2_sem_seg --test_area 5 --log_dir pointnet2_sem_seg PARAMETER ... Namespace(batch_size=16, decay_rate=0.0001, epoch=32, gpu='0', learning_rate=0.001, log_dir='pointnet2_sem_seg', lr_decay=0.7, model='pointnet2_sem_seg', npoint=4096, optimizer='Adam',...
