RandLA-Net-pytorch
RandLA-Net-pytorch copied to clipboard
qiqihaer
RandLA-Net's implementation with Pytorch
I got a bug when I run python main_SemanticKITTI.py **** EPOCH 000 **** 2022-08-01 17:14:40.759397 /media/wx/HDD/DQ/RandLA-Net-pytorch-master/RandLANet.py:265: UserWarning: torch.range is deprecated and will be removed in a future release because its...
Thank you for uploading this code,but you havn't mention how to test or visualize the result.Would you like to supply the code or method?
Hi, thank you to your work, it is very useful for me. BTW, looking at the model structure I noticed a difference with the original network, in the last decoder...
The sampling point is selected according to the probability value. Will it not break the corresponding relationship between the probability value and the point if the sequence of data is...
I test it on area5, why the performance on S3DIS is much lower than official code(the tensorflow version) ?
Hi @qiqihaer ,Thanks for your code . I trained the network for 100 epochs ,but the mean iou only reached 48.1. Do you know the reason?
Hi,@qiqihaer ,Thanks for your reproducing the work in PyTorch. Because I want to get the prediction of all point in each frame,but I found that Randla-Net and KPConv both do...
Hi, According to the paper: Random Sampling (RS): We implement random sam- pling with the python numpy package. Specifically, we first use the numpy function numpy.random.choice() to generate K indices....
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 3.5. Currently, no more support is...
