search

eladrich / pixel2style2pixel

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework
https://eladrich.github.io/pixel2style2pixel/
MIT License
3.2k stars 568 forks source link

ninja compilation error #296

Closed AkhileshV closed 2 years ago

AkhileshV commented 2 years ago

What are the visual studio and CUDA versions required for successful ninja compilation? I have visual studio 2019 and CUDA 11.2! Ninja compilation throws an error saying

"C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\bin\Hostx86\x86/link.exe" fused_bias_act.o fused_bias_act_kernel.cuda.o /nologo /DLL c10.lib c10_cuda.lib torch_cpu.lib torch_cuda_cu.lib -INCLUDE:?_torch_cuda_cu_linker_symbol_op_cuda@native@at@@YA?AVTensor@2@AEBV32@@Z torch_cuda_cpp.lib -INCLUDE:?warp_size@cuda@at@@YAHXZ torch.lib /LIBPATH:C:\Users\akhil\anaconda3\envs\anc_project\lib\site-packages\torch\lib torch_python.lib /LIBPATH:C:\Users\akhil\anaconda3\envs\anc_project\libs "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2\lib/x64" cudart.lib /out:fused.pyd FAILED: fused.pyd "C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\bin\Hostx86\x86/link.exe" fused_bias_act.o fused_bias_act_kernel.cuda.o /nologo /DLL c10.lib c10_cuda.lib torch_cpu.lib torch_cuda_cu.lib -INCLUDE:?_torch_cuda_cu_linker_symbol_op_cuda@native@at@@YA?AVTensor@2@AEBV32@@Z torch_cuda_cpp.lib -INCLUDE:?warp_size@cuda@at@@YAHXZ torch.lib /LIBPATH:C:\Users\akhil\anaconda3\envs\anc_project\lib\site-packages\torch\lib torch_python.lib /LIBPATH:C:\Users\akhil\anaconda3\envs\anc_project\libs "/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2\lib/x64" cudart.lib /out:fused.pyd LINK : fatal error LNK1104: cannot open file 'kernel32.lib' ninja: build stopped: subcommand failed.

Also does the project not work on windows? I saw the prerequisites as Linux/macOS

yuval-alaluf commented 2 years ago

Regarding the question about windows, there are some people that got the code working on windows. Take a look at some of the older issues for clarification on that. Although I will say that I have never tried to run it on windows myself.

I believe that your working on windows is resulting in the ninja compilation problem. Therefore, try to see what others did to get the code working on ninja and hopefully this will also resolve your issue.

AkhileshV commented 2 years ago

Okay! Thank you!

NithinJangid commented 1 year ago

Hello @AkhileshV did you solved the problem? if yes, would you tell me how did you solve it