James Betker eb11a08d1c Enable disjoint feature networks ... This is done by pre-training a feature net that predicts the features of HR images from LR images. Then use the original feature network and this new one in tandem to work only on LR/Gen images.		2020-07-31 16:29:47 -06:00
..
__init__.py
arch_util.py
AttentionResnet.py
discriminator_vgg_arch.py	Fix SRG4 & switch disc	2020-07-25 17:16:54 -06:00
DiscriminatorResnet_arch_passthrough.py
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
ProgressiveSrg_arch.py	Add a way to disable grad on portions of the generator graph to save memory	2020-07-22 11:40:42 -06:00
ResGen_arch.py
RRDBNet_arch.py
spinenet_arch.py
SRG1_arch_new.py
SRG1_arch.py
SRResNet_arch.py
SwitchedResidualGenerator_arch.py	Fix SRG4 & switch disc	2020-07-25 17:16:54 -06:00