Page 1 of 1

are models in faceswap just architecture or pre-trained

Posted: Tue Aug 16, 2022 8:27 pm
by damingxing

out of curiosity, for the models from faceswap (iae, villain, phaze-a...)

  1. are they just architecture, meaning we train them with our data from scratch (starting from random weights)?
    or
  2. are they pre-trained models; we are just fine-tunning them with our data (videos)?

Thanks!


Re: are models in faceswap just architecture or pre-trained

Posted: Wed Aug 17, 2022 8:44 am
by torzdf

You are training them from scratch, unless you choose to load/freeze weights from a previously trained model.