yunlu-chen / pointmixup Goto Github PK

When I apply "sh setup.sh", the following error will appear.
“
Traceback (most recent call last):
File "setup.py", line 34, in
"nvcc": ["-O2", "-I{}".format("{}/include".format(_ext_src_root))],
File "/public/data1/users/liangyaqian/.conda/envs/pytorch-3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 867, in CUDAExtension
library_dirs += library_paths(cuda=True)
File "/public/data1/users/liangyaqian/.conda/envs/pytorch-3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 975, in library_paths
if (not os.path.exists(_join_cuda_home(lib_dir)) and
File "/public/data1/users/liangyaqian/.conda/envs/pytorch-3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1982, in _join_cuda_home
raise EnvironmentError('CUDA_HOME environment variable is not set. '
OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.
Traceback (most recent call last):
File "setup.py", line 9, in
'emd/emd_cuda.cu',
File "/public/data1/users/liangyaqian/.conda/envs/pytorch-3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 867, in CUDAExtension
library_dirs += library_paths(cuda=True)
File "/public/data1/users/liangyaqian/.conda/envs/pytorch-3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 975, in library_paths
if (not os.path.exists(_join_cuda_home(lib_dir)) and
File "/public/data1/users/liangyaqian/.conda/envs/pytorch-3/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1982, in _join_cuda_home
raise EnvironmentError('CUDA_HOME environment variable is not set. '
OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.
setup.sh: line 8: cd: cd: No such file or directory
”
How should I solve this problem?

@yunlu-chen thanks for ur work , what is the timeline for releasing your code !!!!!!!!!!!

Hi! Thank you so much for your impressive work. I am very interested in the few-shot experiment, can you release the corresponding code? Thanks.

Hi,
Thanks for the interesting work! I have a question about the manifold mixup. Does it equal to batch normalization when batch size = 2? Is batch norm a non-OA version of manifold mixup? Thanks.

Dear Authors,

Thank you so much for this nice repo. We recently proposed a new corruption robustness benchmark called ModelNet40-C and test PointMixup on several corruptions from our dataset. We find that PointMixup is robust to "transformation" corruptions.
Github repo: https://github.com/jiachens/ModelNet40-C
Paper link: https://arxiv.org/abs/2201.12296

I wonder if you can mention our benchmark and dataset in your repo to highlight the results. Thank you!

Hello,
I've been going through the repository but I cannot figure out which module/function to use if I want to generate an interpolation between two point clouds. I intend to use this to augment my dataset. Is there such a function in the repository?

Best regards
Love Nordling

Hi! From my paper understanding you use two different versions of ModelNet40, one pre-aligned in experiments with DGCNN and the other un-aligned for PointNet++ experiments. Can you kindly point me to the specific versions used in your experimental setting (downloading links maybe)?
Thanks

when I run this code pip install git+git://github.com/erikwijmans/[email protected]#egg=etw_pytorch_utils,
It appears Collecting etw_pytorch_utils
Cloning git://github.com/erikwijmans/etw_pytorch_utils.git (to revision v1.1.1) to /tmp/pip-install-pm9z2bgw/etw-pytorch-utils_22ef78411dde49a3b30c66bfb814949e
Running command git clone --filter=blob:none --quiet git://github.com/erikwijmans/etw_pytorch_utils.git /tmp/pip-install-pm9z2bgw/etw-pytorch-utils_22ef78411dde49a3b30c66bfb814949e
fatal: unable to connect to github.com:
github.com[0: 20.205.243.166]: errno=Connection timed out

error: subprocess-exited-with-error

× git clone --filter=blob:none --quiet git://github.com/erikwijmans/etw_pytorch_utils.git /tmp/pip-install-pm9z2bgw/etw-pytorch-utils_22ef78411dde49a3b30c66bfb814949e did not run successfully.
│ exit code: 128
╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error

× git clone --filter=blob:none --quiet git://github.com/erikwijmans/etw_pytorch_utils.git /tmp/pip-install-pm9z2bgw/etw-pytorch-utils_22ef78411dde49a3b30c66bfb814949e did not run successfully.
│ exit code: 128
╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.
How can I solve this problem?

I am using pytroch-1.8.1, cuda-10.1 and python 3.6.
After compiling the emd, I import torch and emd. However, an error occurs:

ImportError: /root/anaconda3/envs/pc/lib/python3.6/site-packages/emd-0.0.0-py3.6-linux-x86_64.egg/emd.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZNK2at6Tensor4sizeEl

error to run "pip install git+git://github.com/erikwijmans/[email protected]#egg=etw_pytorch_utils"
then I find the link "http://github.com/erikwijmans/etw_pytorch_utils“ is not found, do you know how to solve it?