Giters

omerbt / Splice

Official Pytorch Implementation for "Splicing ViT Features for Semantic Appearance Transfer" presenting "Splice" (CVPR 2022 Oral)

Home Page:https://splice-vit.github.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

问问配置

yuchen202 opened this issue · comments

commented

请问跑这个模型的配置是啥

commented

I guess you may need one gpu with 16G RAM. I only have the 12G one, so I modified the config to resize the picture. What make me confused is that the model is trained with only one pair of pictures, which means we have to train N models for N pairs of pictures. I don't know if my guess is correct.