James Betker 6c6e82406e Pass a corruption factor through the dataset into the upsampling network ... The intuition is this will help guide the network to make better informed decisions about how it performs upsampling based on how it perceives the underlying content. (I'm giving up on letting networks detect their own quality - I'm not convinced it is actually feasible)		2021-06-07 09:13:54 -06:00
..
byol	Clean up byol a bit	2021-05-24 21:35:46 -06:00
classifiers	Another fix to anorm	2021-06-06 15:09:49 -06:00
diffusion	Pass a corruption factor through the dataset into the upsampling network	2021-06-07 09:13:54 -06:00
fixup_resnet
flownet2@db2b7899ea
glean
global_convs
optical_flow
pixel_level_contrastive_learning
segformer	Clean up byol a bit	2021-05-24 21:35:46 -06:00
srflow
styled_sr
stylegan	misc adjustments for stylegan	2021-04-21 18:14:17 -06:00
switched_conv	Another fix to anorm	2021-06-06 15:09:49 -06:00
tecogan
transformers
vqvae
__init__.py
arch_util.py
discriminator_vgg_arch.py
feature_arch.py
lightweight_gan.py
ResGen_arch.py
RRDBNet_arch.py
spinenet_arch.py