I am looking to generate groundtruth for ScanNet dataset using the tools/generate_gt.py.
I am running the following command as provided by you python tools/generate_gt.py --save_name planes_9/ --window_size 9 --n_proc 2 --n_gpu 1.
But I find that the script is stuck in the load stage in file : tools/ChamferDistancePytorch/chamfer3D/dist_chamfer_3D.py
When I kill the job using Ctrl + c. I see that the following stack.
File "tools/generate_gt.py", line 33, in <module>
from tools.ChamferDistancePytorch.chamfer3D import dist_chamfer_3D
File "./tools/ChamferDistancePytorch/chamfer3D/dist_chamfer_3D.py", line 19, in <module>
], build_directory=build_path)
File "/home/us000146/anaconda3/envs/selfsupervised/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1091, in load
keep_intermediates=keep_intermediates)
File "/home/us000146/anaconda3/envs/selfsupervised/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1306, in _jit_compile
baton.wait()
File "/home/us000146/anaconda3/envs/selfsupervised/lib/python3.6/site-packages/torch/utils/file_baton.py", line 42, in wait
time.sleep(self.wait_seconds)
KeyboardInterrupt
PS: I find that chamfer_cuda.cpp and chamfer3D.cu are present.
Could you please suggest what I might be missing here.
Hey @ymingxie ,
I am looking to generate groundtruth for ScanNet dataset using the
tools/generate_gt.py
.I am running the following command as provided by you
python tools/generate_gt.py --save_name planes_9/ --window_size 9 --n_proc 2 --n_gpu 1
. But I find that the script is stuck in theload
stage in file :tools/ChamferDistancePytorch/chamfer3D/dist_chamfer_3D.py
from torch.utils.cpp_extension import load chamfer_3D = load(name="chamfer_3D", sources=[ "/".join(os.path.abspath(__file__).split('/')[:-1] + ["chamfer_cuda.cpp"]), "/".join(os.path.abspath(__file__).split('/')[:-1] + ["chamfer3D.cu"]), ], build_directory=build_path)
and is not moving forward.
When I kill the job using
Ctrl + c
. I see that the following stack.PS: I find that
chamfer_cuda.cpp
andchamfer3D.cu
are present. Could you please suggest what I might be missing here.