Hangz-nju-cuhk / Talking-Face-Generation-DAVS

Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)
MIT License
819 stars 173 forks source link

Unzipping pretrained model issues #33

Closed AtaUllahB closed 5 years ago

AtaUllahB commented 5 years ago

Unable to unzip pretrained model(checkpoint.pth.tar) in both Windows and Ubuntu. windows ubuntu

Hangz-nju-cuhk commented 5 years ago

@TalkingPictures in order to load this checkpoint to pytorch, you do not need to unzip it. Simply use what I wrote: 'torch.load' is enough. But sorry as I write in the email, I do not know how to convert it to tensorflow checkpoint file for now.

AtaUllahB commented 5 years ago

@Hangz-nju-cuhk Thank you for replying. I'll let you know if we make any progress in this regard.