Is the point transformer of contrastBoundary environment same with the original point transformer?

[whuhxb]

Hi @LiyaoTang

Is the point transformer of contrastBoundary environment same with the original point transformer? I ran the original point transformer successfully. But recently, I can't run through the point transformer of contrastBoundary.

The bugs show up as below. I have checked there are empty GPU cards. Thanks.

model = torch.nn.DataParallel(model.cuda()) File "/export/home/hanxiaobing/anaconda3/envs/pt_CBL/lib/python3.7/site-packages/torch/nn/modules/module.py", line 637, in cuda return self._apply(lambda t: t.cuda(device)) File "/export/home/hanxiaobing/anaconda3/envs/pt_CBL/lib/python3.7/site-packages/torch/nn/modules/module.py", line 530, in _apply module._apply(fn) File "/export/home/hanxiaobing/anaconda3/envs/pt_CBL/lib/python3.7/site-packages/torch/nn/modules/module.py", line 530, in _apply module._apply(fn) File "/export/home/hanxiaobing/anaconda3/envs/pt_CBL/lib/python3.7/site-packages/torch/nn/modules/module.py", line 530, in _apply module._apply(fn) File "/export/home/hanxiaobing/anaconda3/envs/pt_CBL/lib/python3.7/site-packages/torch/nn/modules/module.py", line 552, in _apply param_applied = fn(param) File "/export/home/hanxiaobing/anaconda3/envs/pt_CBL/lib/python3.7/site-packages/torch/nn/modules/module.py", line 637, in return self._apply(lambda t: t.cuda(device)) File "/export/home/hanxiaobing/anaconda3/envs/pt_CBL/lib/python3.7/site-packages/torch/cuda/init.py", line 172, in _lazy_init torch._C._cuda_init() RuntimeError: No CUDA GPUs are available

[LiyaoTang]

By in large, yes. But you need to re-compile the ops.