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
..
__init__.py
arch_util.py	Add simplified SPSR architecture	2020-08-03 10:25:37 -06:00
AttentionResnet.py	Add attention resnet	2020-05-29 20:02:10 -06:00
discriminator_vgg_arch.py	Crossgan	2020-08-07 21:03:39 -06:00
DiscriminatorResnet_arch_passthrough.py	Allow passthrough discriminator to have passthrough disabled from config	2020-05-19 09:41:16 -06:00
DiscriminatorResnet_arch.py
feature_arch.py	Enable disjoint feature networks	2020-07-31 16:29:47 -06:00
FlatProcessorNet_arch.py
FlatProcessorNetNew_arch.py
HighToLowResNet.py
NestedSwitchGenerator.py	Move ExpansionBlock to arch_util	2020-07-10 15:53:41 -06:00
ProgressiveSrg_arch.py	Don't recompute generator outputs for D in standard operation	2020-08-04 11:28:52 -06:00
ResGen_arch.py	More NSG improvements (v3)	2020-06-29 20:26:51 -06:00
RRDBNet_arch.py	Remove RRDB with switching	2020-07-01 12:08:32 -06:00
spinenet_arch.py	SRG3 work	2020-07-07 13:46:40 -06:00
SPSR_arch.py	LR switched SPSR arch	2020-08-10 13:03:36 -06:00
SPSR_util.py	Add simplified SPSR architecture	2020-08-03 10:25:37 -06:00
SRG1_arch_new.py	Remove all biases from generator	2020-07-04 22:19:55 -06:00
SRG1_arch.py	Move ExpansionBlock to arch_util	2020-07-10 15:53:41 -06:00
SRResNet_arch.py
SwitchedResidualGenerator_arch.py	LR switched SPSR arch	2020-08-10 13:03:36 -06:00