Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Issue of upfirdn2d while training stylegan2 #314

Open
Anee115 opened this issue Dec 13, 2024 · 0 comments
Open

Issue of upfirdn2d while training stylegan2 #314

Anee115 opened this issue Dec 13, 2024 · 0 comments

Comments

@Anee115
Copy link

Anee115 commented Dec 13, 2024

Describe the bug

  • OS: [Windows 11]
  • PyTorch torch===1.7.1+cu110 torchvision===0.8.2+cu110 torchaudio===0.7.2
  • CUDA toolkit version (e.g., CUDA 11.0)
  • GPU [RTX 4060]
    okay, the issue comes while training. while training I had an issue with upfirdn2d.
    initially, I was working with Cudatoolkit 12.3 version and Visual Studio Community 2022
    but after one week's struggle I read the previous comments on this issue, Today I made a new env. from scratch with Python 3.7 changed my cuda from 12.1 to 11.0 and installed it in the system. I even changed the path to it and rebooted the system again, and then I changed the version of VS 2020 -VS 2019 community edition. and then start the C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Auxiliary\Build\vcvars64.bat file.Rebooted the system again. Then I reinstalled all the libs from scratch in my new environment. after that, I start training my file (train.py).
    initially, it started working and created the parameters but then showed me error but after that when I moved toward the output directory I found 7 files.
Screenshot 2024-12-13 164102 but still I got a lot of errors of only this upfirdn2d.

Traceback (most recent call last):
File "C:\WINDOWS\system32\temp\stylegan2-ada-pytorch\torch_utils\ops\upfirdn2d.py", line 32, in _init
_plugin = custom_ops.get_plugin('upfirdn2d_plugin', sources=sources, extra_cuda_cflags=['--use_fast_math'])
File "C:\WINDOWS\system32\temp\stylegan2-ada-pytorch\torch_utils\custom_ops.py", line 111, in get_plugin
torch.utils.cpp_extension.load(name=module_name, verbose=verbose_build, sources=sources, **build_kwargs)
File "C:\Users\aneek\anaconda3\envs\video_gan_env\lib\site-packages\torch\utils\cpp_extension.py", line 997, in load
keep_intermediates=keep_intermediates)
File "C:\Users\aneek\anaconda3\envs\video_gan_env\lib\site-packages\torch\utils\cpp_extension.py", line 1213, in _jit_compile
return _import_module_from_library(name, build_directory, is_python_module)
File "C:\Users\aneek\anaconda3\envs\video_gan_env\lib\site-packages\torch\utils\cpp_extension.py", line 1560, in _import_module_from_library.

Screenshots

Screenshot 2024-12-13 163745
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant