James Betker 59aba1daa7 LR switched SPSR arch ... This variant doesn't do conv processing at HR, which should save a ton of memory in inference. Lets see how it works.		2020-08-10 13:03:36 -06:00
..
archs	LR switched SPSR arch	2020-08-10 13:03:36 -06:00
__init__.py	Integrate SPSR into SRGAN_model	2020-08-02 12:55:08 -06:00
base_model.py	Fix multistep optimizer (feeding from wrong config params)	2020-08-04 16:42:58 -06:00
feature_model.py	Add feature_model for training custom feature nets	2020-07-31 11:20:39 -06:00
loss.py	Crossgan	2020-08-07 21:03:39 -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	LR switched SPSR arch	2020-08-10 13:03:36 -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	Crossgan	2020-08-07 21:03:39 -06:00