[ICCV 2021] Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
Wuchuq opened this issue 2 years ago · comments
when I use the pretrained model in stage 1 for "resume", it is shown that the model doesn't fit. So how should the training for stage 2 use the pretrained model in stage1?