yunlu-chen / pointmixup Goto Github PK
View Code? Open in Web Editor NEWImplementation for paper "PointMixup: Augmentation for Point Cloud". Accepted to ECCV 2020 as spotlight presentation
Implementation for paper "PointMixup: Augmentation for Point Cloud". Accepted to ECCV 2020 as spotlight presentation
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
raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str))
RuntimeError: DataLoader worker (pid(s) 386672, 386673, 386674, 386675, 386676, 386677, 386678, 386679, 386680, 386681) exited unexpectedly
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?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.