ninja: build stopped: subcommand failed.

[Max-boot]

Describe the bug
Cant

To Reproduce
Steps to reproduce the behavior:

1. Run the normal generate image or generate video thing
2. Acts normally until the bias_act step
3. crashes

Full crash log for anyone interested
crash log.txt
Please copy&paste text instead of screenshots for better searchability.

Expected behavior
It probably shouldnt have crashed, since I didnt change anything inside of the code

Screenshots
If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

• OS: Win 11
• Enviroment: name: stylegan3
  channels:
  • pytorch
  • nvidia
    dependencies:
  • python >= 3.8
  • pip
  • numpy>=1.20
  • click>=8.0
  • pillow=8.3.1
  • scipy=1.7.1
  • pytorch=1.9.2
  • cudatoolkit=11.1
  • requests=2.26.0
  • tqdm=4.62.2
  • ninja=1.11.1.1
  • matplotlib=3.4.2
  • imageio=2.9.0
  • pip:
    • imgui==1.3.0
    • glfw==2.2.0
    • pyopengl==3.1.5
    • imageio-ffmpeg==0.4.3
    • pyspng
• CUDA toolkit version (e.g., CUDA 11.1.1)
• NVIDIA driver version
• GPU RTX 3070 Aurorus Master
• Docker: no docker in use

Additional context
I didnt change the code and Im using Visual Studio 2022

[Neilstid]

Hi,

this is a classic issue for windows user (as I am ;)). You can check these issues to help:

• 'utf-8' codec can't decode byte 0xd5 in position 1142: invalid continuation byte #638
• ninja: build stopped: subcommand failed. #640

Based on the provided information, this is most likely because you do not have a C compiler. Therefore, since StyleGAN have some JIT code, you need to have Clang (described #638). If it remains after Clang, it means you have some issues with Cuda (#640)