DL-Art-School/codes/models/steps
James Betker ea56eb61f0 Fix DDP errors for discriminator
- Don't define training_net in define_optimizers - this drops the shell and leads to problems downstream
- Get rid of support for multiple training nets per opt. This was half baked and needs a better solution if needed
   downstream.
2020-12-07 12:50:57 -07:00
..
__init__.py ExtensibleTrainer work 2020-08-22 08:24:34 -06:00
injectors.py iGPT support! 2020-12-03 15:32:21 -07:00
losses.py iGPT support! 2020-12-03 15:32:21 -07:00
progressive_zoom.py Fixes and additional support for progressive zoom 2020-10-30 09:59:54 -06:00
steps.py Fix DDP errors for discriminator 2020-12-07 12:50:57 -07:00
stereoscopic.py Fixes to unified chunk datasets to support stereoscopic training 2020-10-26 11:12:22 -06:00
tecogan_losses.py Mods to tecogan to allow use of embeddings as input 2020-11-24 09:24:02 -07:00