search

VinAIResearch / WaveDiff

Official Pytorch Implementation of the paper: Wavelet Diffusion Models are fast and scalable Image Generators (CVPR'23)
GNU Affero General Public License v3.0
364 stars 28 forks source link

ninja problem #11

Open poxiao0 opened 7 months ago

poxiao0 commented 7 months ago

When I use the pretrained weights to test the result by a GPU on celeba_256 dataset, it occurs following preblem. I can not solve it, can you give me some advice?

Traceback (most recent call last): File "/home/wbx/anaconda3/envs/wavediff/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1723, in _run_ninja_build env=env) File "/home/wbx/anaconda3/envs/wavediff/lib/python3.7/subprocess.py", line 512, in run output=stdout, stderr=stderr) subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

quandao10 commented 7 months ago

I think you could try pip install ninja. If it is not working, try conda install -c conda-forge cudatoolkit-dev.

poxiao0 commented 7 months ago

I think you could try pip install ninja. If it is not working, try conda install -c conda-forge cudatoolkit-dev.

Thank you advice but these two advice are not valid. I can not resolve this problem.

ZXXaaaa commented 2 months ago

Hello, I meet the same problem. Have you solved it?

poxiao0 commented 2 months ago

Hello, I meet the same problem. Have you solved it?

Finally,I use the way from stylegan2. I suggest you to see its comments.

ZXXaaaa commented 2 months ago

OK, thanks for your answer.