DL-Art-School/codes/models/archs
James Betker df1046c318 New arch: SwitchedResidualGenerator_arch
The concept here is to use switching to split the generator into two functions:
interpretation and transformation. Transformation is done at the pixel level by
relatively simple conv layers, while interpretation is computed at various levels
by far more complicated conv stacks. The two are merged using the switching
mechanism.

This architecture is far less computationally intensive that RRDB.
2020-06-16 11:23:50 -06:00
..
__init__.py mmsr 2019-08-23 21:42:47 +08:00
arch_util.py Fix initialization in mhead switched rrdb 2020-06-15 21:32:03 -06:00
AttentionResnet.py Add attention resnet 2020-05-29 20:02:10 -06:00
discriminator_vgg_arch.py Separate feature extractors out, add resnet feature extractor 2020-05-28 20:26:30 -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 Fixup upconv for the next attempt! 2020-05-01 19:56:14 -06:00
feature_arch.py Fix process_video bugs 2020-05-29 12:47:22 -06:00
FlatProcessorNet_arch.py Add more batch norms to FlatProcessorNet_arch 2020-04-30 11:47:21 -06:00
FlatProcessorNetNew_arch.py Full resnet corrupt, no BN 2020-04-30 19:17:30 -06:00
HighToLowResNet.py Misc changes 2020-04-28 11:50:16 -06:00
ResGen_arch.py Apply fixes to resgen 2020-05-24 07:43:23 -06:00
RRDBNet_arch.py Fix initialization in mhead switched rrdb 2020-06-15 21:32:03 -06:00
SRResNet_arch.py mmsr 2019-08-23 21:42:47 +08:00
SwitchedResidualGenerator_arch.py New arch: SwitchedResidualGenerator_arch 2020-06-16 11:23:50 -06:00