search

yuval-alaluf / stylegan3-editing

Official Implementation of "Third Time's the Charm? Image and Video Editing with StyleGAN3" (AIM ECCVW 2022) https://arxiv.org/abs/2201.13433
https://yuval-alaluf.github.io/stylegan3-editing/
MIT License
654 stars 73 forks source link

Runing environment on SM_86 GPU Architecture Ampere #12

Closed hqnicolas closed 2 years ago

hqnicolas commented 2 years ago

when using a newer graphics card （ like nvidia. GeForce RTX 3090） because the architecture of the graphics card is relatively new ， maybe the older version of the pytorch library does not support the 。 that's when it will show up. capability sm_86 is not compatible at the same time, according to the output, you can see The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70 sm_75 currently, pytorch can only support the above architectures.

yuval-alaluf commented 2 years ago

It seems like you need to upgrade your PyTorch version to be compatible with the CUDA version of the 3090 GPU. There are numerous forums on the PyTorch website like this one which can help you out.

yuval-alaluf commented 2 years ago

Just to verify, this solved your issue with running on the SM_86 architecture?

yuval-alaluf commented 2 years ago

Cool. Thanks for the info! Closing for now :)