Pointnet2.ScanNet icon indicating copy to clipboard operation
Pointnet2.ScanNet copied to clipboard

PointNet++ Semantic Segmentation on ScanNet in PyTorch with CUDA acceleration

Results 7 Pointnet2.ScanNet issues
Sort by recently updated
recently updated
newest added

Hi, @daveredrum I'm happy to meet your wonderful code! I have a question about 'CK''s meaning in eval.py. I think N is num of points and C is num of...

Hi, I find it hard to understand what is going on with the data chunks generation process in the file below. https://github.com/daveredrum/Pointnet2.ScanNet/blob/f4adc43779aaaefd6138d37183a94185d0718865/lib/dataset.py#L219-L240 1. What is line 236 meant for? 2....

The `GroupAll` module receives `ret_grouped_xyz` in its constructor but never sets it as a member. However, `self.ret_grouped_xyz` is still being used in the forward call. This PR fixes this issue.

Hi, My environment is: Ubuntu 18.04 Python 3.9.0 PyTorch 1.12.0 with CUDA 11.3 GeForce RTX 3090 GPU (Unable to use cuda 10.1) When I install pointnet2 with CUDA 11.3, I...

- Which ScanNet data you used (ex. scene0041_00), especially in second pretrained model? - Also, how many epochs it required?

Can I use PyTorch 2.1.0 and cuda 11.8 for compile the package?