James Betker 696242064c Use tensor checkpointing to drastically reduce memory usage ... This comes at the expense of computation, but since we can use much larger batches, it results in a net speedup.		2020-09-03 11:33:36 -06:00
..
__init__.py
arch_util.py	Reference network	2020-08-25 11:56:59 -06:00
AttentionResnet.py
discriminator_vgg_arch.py	Fix vgg_gn input_img_factor	2020-08-31 09:50:30 -06:00
DiscriminatorResnet_arch_passthrough.py
DiscriminatorResnet_arch.py
feature_arch.py
FlatProcessorNet_arch.py
FlatProcessorNetNew_arch.py
HighToLowResNet.py
NestedSwitchGenerator.py
ProgressiveSrg_arch.py	Don't recompute generator outputs for D in standard operation	2020-08-04 11:28:52 -06:00
ResGen_arch.py
RRDBNet_arch.py
spinenet_arch.py
SPSR_arch.py	4x spsr ref (not workin)	2020-08-29 09:27:18 -06:00
SPSR_util.py
SRG1_arch_new.py
SRG1_arch.py
SRResNet_arch.py
SwitchedResidualGenerator_arch.py	Use tensor checkpointing to drastically reduce memory usage	2020-09-03 11:33:36 -06:00