LianShuaiLong comments

Results 4 comments of


LianShuaiLong

how can i load the trained-model

when i change the state_dict by: from collections import OrderedDict state_dict = torch.load('model.pth') new_state_dict = OrderedDict() for k,v in state_dict.items(): new_key = k.strip('model.') new_state_dict[new_key] = v model.load_state_dict(new_state_dict) the following errors...

Mismatch between number of poses and images

The same error. I wonder what type data do we need to run demo.sh , images in JPG,PNG format is enough?

Doubts about KL loss

> I'm joining the doubts about the KL term. > But before that, let me try to address your two cases: > > 1. The same shape tensor outputs the...

I keep getting this error does anyone have a solution? _ raise Exception("Failed in loading audio2pose_checkpoint") Exception: Failed in loading audio2pose_checkpoint

> > you can try to download all checkpoints from this https://raw.githubusercontent.com/Winfredy/SadTalker/main/scripts/download_models.sh, and put them to `SADTALKER_CHECKPOINTS` 's **checkpoints** directory. > > Download all files. Set the file path to...