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

Problem with run model on CPU #54

Open Violino1Ann opened 4 years ago

Violino1Ann commented 4 years ago

How to run the model on CPU? I want to generate an image of a rabbit but there is a problem after I set coda_on=False, mul_gpu=False and load pretrained models with map_location=torch.device('cpu'). I got almost gray images in "results" folder with some attributes that show this image is not empty as in example.