RandLA-Net-pytorch
RandLA-Net-pytorch copied to clipboard
aRI0U
PyTorch implementation of RandLA-Net
When I tested the s3dis data set, I encountered the error "ValueError: attempt to get argmin of an empty sequence". I found that path="xxx/subsample/test",loader,_=data_loaders(path); in the test.py file; but there...
Hi, In file **model.py** class **LocalSpatialEncoding** function **forward** the line: **features.expand(B, -1, N, K)** replicates the feature of the anchor point K times. According to my understanding of the paper...
can i get a knn algorithm in model.py as import and line 172. I have a several promblems on import torch_points_kernels and torch_points.
Hi there. Using CUDA version of local spatial encoding in the 'gather' branch (#17) will get the following error: > RuntimeError: Expected all tensors to be on the same device,...
Hi Sir ;  I have downloaded the dataset, but to process this data I get this error message, do I have to convert this data to .npy format if...
I have noticed that there comes torch.distributions.utils.probs_to_logits after forward propagation: train.py 115~117: ``` scores = model(points)#[b, 40960, 6]->[b, 14, 40960] logp = torch.distributions.utils.probs_to_logits(scores, is_binary=False) ``` why needs torch.distributions.utils.probs_to_logits? Can I...
Question about Semantic3d data preparation. Why are we converting point clouds to .npy instead of .ply format? Is this more convenient when using PyTorch? faster to read? I have seen...
I wanted to use RandLA-Net for my research-work. But, I am unable to run your github codes because of the compatibility issues with Python. Could you please help me to...
Hi Ariou, thanks for sharing the code. I forked your code and trained on S3DIS. However, the loss was not to converge and IoUs of many classes maintained 0. Do...
Hello @aRI0U @Thibaud-Ardoin , thanks for sharing your implementation, I am very excited to start using it. I am having troubles understanding exactly how to run your code, however. 1...
