DeepFaceLab
DeepFaceLab copied to clipboard
Python crashes when starting training.
run train SAEHD.bat or train AMP.bat input all the parameters. all samples loading. and after it hits 100% Python crashes. No other errors. I use DeepFaceLab_DirectX12_build_05_04_2022 with RTX 3070
- Operating system and version: Windows 10 Pro 20H2
-
Python version: python-3.6.8(that comes with deepfacelab)
Yyhgg
Most of us don't read Russian so a translation of that error on screen would be nice, with that said, in this case the error is generic so not helpful. You haven't listed any model parameters in this issue so I will have to make some assumptions. Try turning "Place Models and optimizer on GPU" OFF.
yea that error is generic that Python stopped working and shut down the program. all model parameters are on default(except batch size value is on 4 as on 8 it doesnt start at all.) as i dont know what to change. so its DeepFaceLab_DirectX12_build_05_04_2022 downloaded extracted and everything on default except batch size value is on 4 as on 8 it doesnt start at all. and tried turning "Place Models and optimizer on GPU" OFF. same thing Python stopped working. with no errors.
eh nothing =(
having this same issue, is this solved? @gregtorn (https://github.com/iperov/DeepFaceLab/assets/75314910/086836e8-50b4-4a9e-8387-f18559eec997)) python stops working and pops up 4 error windows.
Did you ever find the answer? If so, would you mind sharing it and closing this issue?
Same issue here, any fixes available?
Same issue for me, no solution yet