PrashanthaTP

Results 4 comments of PrashanthaTP

For sync disriminator + it should be trained seperately for x epochs till generator can generate fair images of face + it helps sync disc to focus on lips then...

Things that help + Large dataset with different actors,with equal distribution of genders + Training sync discriminator seperately initially as done in [wav2lip](https://github.com/Rudrabha/Wav2Lip). +

Yeah, seems good to me. Also we can merge options and hparams into one, options = store(options,hparams,config) so we can call ```python def function(options,...): ... = options.config ... = options.hparams...