James Betker 4bfbdaf94f Don't recompute generator outputs for D in standard operation ... Should significantly improve training performance with negligible results differences.		2020-08-04 11:28:52 -06:00
..
archs	Don't recompute generator outputs for D in standard operation	2020-08-04 11:28:52 -06:00
__init__.py	Integrate SPSR into SRGAN_model	2020-08-02 12:55:08 -06:00
base_model.py	Add feature_model for training custom feature nets	2020-07-31 11:20:39 -06:00
feature_model.py	Add feature_model for training custom feature nets	2020-07-31 11:20:39 -06:00
loss.py	Substantial SPSR mods & fixes	2020-08-02 10:45:24 -06:00
lr_scheduler.py	Allow multi_step_lr_scheduler to load a new LR schedule when restoring state	2020-07-31 11:21:11 -06:00
networks.py	Add simplified SPSR architecture	2020-08-03 10:25:37 -06:00
SPSR_model.py	Integrate SPSR into SRGAN_model	2020-08-02 12:55:08 -06:00
SR_model.py	Allow validating in batches, remove val size limit	2020-06-02 08:41:22 -06:00
SRGAN_model.py	Don't recompute generator outputs for D in standard operation	2020-08-04 11:28:52 -06:00