PU-Net_pytorch
PU-Net_pytorch copied to clipboard
lyqun
PyTorch Implementation of PU-Net. PU-Net: Point Cloud Upsampling Network, CVPR 2018
hi why i run the bash test_punet.sh, it happen that "no modul named knn_cuda import KNN"? i run this code with cuda9.0 python 3.6 pytorch1.0
Namespace(alpha=1.0, batch_size=32, decay_step_list=[30, 60], gpu=0, log_dir='logs/test', lr=0.001, lr_clip=1e-06, lr_decay=0.71, max_epoch=100, model='punet', npoint=1024, optim='adam', up_ratio=4, use_bn=False, use_decay=False, use_res=False, weight_decay=0.0005, workers=4) Traceback (most recent call last): File "train.py", line 35, in from...
Hello. I have read the code in the file "auction_match_gpu.cu" for several days, and I try to understand how you calculate the EMD. I have some trouble on reading it....
What are the values of the last three columns of the Patches_noHole_and_collected.h5 data set, which seem to be coordinate data, but are different from the xyz coordinate values of the...
I wanna know why there are still some errors about version when I use python3.6 pytorch1.2 cuda10.0 in anaconda. for example fatal error: cuda_utils.h: No such file or directory
I run the following line, ``` python eval.py --gpu 0 --resume logs/punet_baseline/punet_epoch_99.pth ``` Then, I received the following error ``` (PUNet10) gabby-suwichaya@gabby-suwichaya:/mnt/HDD4TB3/PU-Net_pytorch$ /home/gabby-suwichaya/anaconda3/envs/PUNet10/bin/python /mnt/HDD4TB3/PU-Net_pytorch/auction_match/auction_match.py Traceback (most recent call last): File...
Could you guide how to set the training correct? Or could you please check or confirm this behaviour? ``` (PUNet10) gabby-suwichaya@gabby-suwichaya:/mnt/HDD4TB3/PU-Net_pytorch$ /home/gabby-suwichaya/anaconda3/envs/PUNet10/bin/python /mnt/HDD4TB3/PU-Net_pytorch/train.py Namespace(alpha=1.0, batch_size=4, decay_step_list=[30, 60], gpu=1, log_dir='logs/punet_baseline', lr=0.001,...
After install CGAL, when I run 'make', I meet error, and I can't get evaluation.cpp.o. So, I need your help, hope your reply  
I am trying to upsample lossy compressed point cloud data with PU-Net and I get **four separate different-scales objects**. The data is 8i-people dataset with MPEG TMC13 lossy compressed. Pity...
I tried to use "get_emd_loss.py" but I met this problem RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false. (Could this error message be improved? If so, please report an...
