Note: This tutorial assume you have a suitable GPU and CUDA already setup.
- Open powershell as administrator
- Set-ExecutionPolicy -ExecutionPolicy RemoteSigned
- Invoke-WebRequest -UseBasicParsing -Uri "https://raw.githubusercontent.com/pyenv-win/pyenv-win/master/pyenv-win/install-pyenv-win.ps1" -OutFile "./install-pyenv-win.ps1"; &"./install-pyenv-win.ps1"
- Close and reopen powershell as administrator.
- pyenv install 3.10.11
- pyenv global 3.10.11
- pyenv version
- python -c "import sys; print(sys.executable)"
- cd $env:USERPROFILE
- cd Desktop
- pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 --index-url https://download.pytorch.org/whl/cu117
- pip install root-painter-trainer
- start-trainer
- You will be prompted to input the RootPainter Sync directory. You can just type root_painter_sync and press enter.
- The trainer should now be running and it should tell you your batch size (should be above 0) and if the GPU is available or not (It should say True).