James Betker d1007ccfe7 Adjustments to pixpro to allow training against networks with arbitrarily large structural latents ... - The pixpro latent now rescales the latent space instead of using a "coordinate vector", which **might** have performance implications. - The latent against which the pixel loss is computed can now be a small, randomly sampled patch out of the entire latent, allowing further memory/computational discounts. Since the loss computation does not have a receptive field, this should not alter the loss. - The instance projection size can now be separate from the pixel projection size. - PixContrast removed entirely. - ResUnet with full resolution added.		2021-01-12 09:17:45 -07:00
..
byol	Migrate generators to dynamic model registration	2020-12-24 23:02:10 -07:00
fixup_resnet
flownet2@db2b7899ea
glean	Glean mods	2020-12-27 12:25:06 -07:00
pixel_level_contrastive_learning	Adjustments to pixpro to allow training against networks with arbitrarily large structural latents	2021-01-12 09:17:45 -07:00
srflow	Migrate generators to dynamic model registration	2020-12-24 23:02:10 -07:00
styled_sr	Styled SR fixes	2021-01-05 20:14:39 -07:00
stylegan	More mods to support styledsr	2021-01-04 11:32:28 -07:00
tecogan	Migrate generators to dynamic model registration	2020-12-24 23:02:10 -07:00
transformers	Injector auto-registration	2020-12-29 20:58:02 -07:00
vqvae	Support training imagenet classifier	2021-01-11 20:09:16 -07:00
__init__.py
arch_util.py
discriminator_vgg_arch.py	Misc fixes	2021-01-04 10:53:53 -07:00
feature_arch.py
ResGen_arch.py
resnet_with_checkpointing.py	Support training imagenet classifier	2021-01-11 20:09:16 -07:00
RRDBNet_arch.py	Add injected noise into bypass maps	2021-01-07 16:31:12 -07:00
spinenet_arch.py	Migrate generators to dynamic model registration	2020-12-24 23:02:10 -07:00
weighted_conv_resnet.py	Support training imagenet classifier	2021-01-11 20:09:16 -07:00