How to resume training - Githubissues

facebookresearch / StyleNeRF

This is the open source implementation of the ICLR2022 paper "StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis"

956 stars 92 forks source link

How to resume training #23

Open zhanglonghao1992 opened 2 years ago

zhanglonghao1992 commented 2 years ago

Hi, thanks for your great work! I'm trying to resume training from the released checkpoint ffhq512.pkl. It seems that the super parameters of this released model do not fit any config file (stylenerfffhq*.yaml). Can you provide your config file please?

KyriaAnnwyn commented 2 years ago

Change line 20 in config to upsample_mode: "pixelshuffle"