ninja problem

[poxiao0]

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]

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

[poxiao0]

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]

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

[poxiao0]

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]

OK, thanks for your answer.