James Betker c8ab89d243 Add model swapout ... Model swapout is a feature where, at specified intervals, a random D and G model will be swapped in place for the one being trained. After a short period of time, this model is swapped back out. This is intended to increase training diversity.		2020-05-13 16:53:38 -06:00
..
archs	Allow "corruptor" network to be specified	2020-05-13 15:26:55 -06:00
__init__.py	Implement downsample GAN	2020-04-24 00:00:46 -06:00
base_model.py	Add model swapout	2020-05-13 16:53:38 -06:00
loss.py
lr_scheduler.py
networks.py	Allow "corruptor" network to be specified	2020-05-13 15:26:55 -06:00
SR_model.py	Use amp in SR_model for inference	2020-05-07 21:45:33 -06:00
SRGAN_model.py	Add model swapout	2020-05-13 16:53:38 -06:00
Video_base_model.py