RandLA-Net-pytorch
RandLA-Net-pytorch copied to clipboard
qiqihaer
RandLA-Net's implementation with Pytorch
Did you visualize your result? l found the result on semantickitti is not good.
Hello, thanks for great work. Do you have any plans for semantic3d and s3dis dataloader for your pytorch implementation? I tried, but it seems there are some `business rule' that...
I found that the results I reproduced are similar to yours, but for the same problem, the result of "motorcyclist" is 0.00, and the result of the same "other-ground" is...
Hello, thanks for amazing works. Do you have any idea on what is the main factor for the degradation of performance when to exploit pytorch codes? I want to boost...
Hello, I got errors below, when to experiment with your codes. I think this is a pytorch version issue, thereby i want to know the implementation settings. --- /workspace/gt_cvpr/gt_codes/NewBaseLine/RandLA-Net-pytorch/RandLANet.py:264: UserWarning:...
Hi, thank you for implementing this copy of code. I'd like to ask for the running environment for this copy of code. Also, how I adapt to other datasets?
In RandLANet.py line 69, it is written: f_decoder_i = self.decoder_blocks[j](torch.cat([f_encoder_list[-j - 2], f_interp_i], dim=1)) I'm wondering why not concatenate the f_encoder_list[-j - 1] and f_interp_i?
After reading the code, I found the input is just xyz points, while no features (colors) are included. I'm not sure it is fine?
Hello, I ran the semantic segmentation task of the S3DIS dataset using your previous version of the code. However, I noticed that you had removed this part of the code....
