Zhening Huang
Zhening Huang
same here. Looking for an update
has this been done yet? urgently need this as A100 GPU cannot run this API on cuda 10.2
Hi Loic, Thank you so much for your reply. Could you please point me in the direction of the mean-field partition scheme which is more CUDA-friendly? Maybe get me a...
Same problem here. Did you guys find the solution
Found the problem, make sure you change the val_batch_size in the helper_tool.py
Try to change it to 1, if you have only 1 point cloud to test. I remember there is a calculation that used this variable and if you do not...
Same problem here, the Best miou for me is 67.9. Can you please share you configs please. > I achieve 69.8 for the best miou
found the issue. change all ``` #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ") #define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ") #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x) ``` to...
This package has been used by many other repositories as well and several changes are made to meet different versions of cuda, torch, etc. If this doesn’t work, maybe looking...
This is great! thanks a lot! looking forward to it!