James Betker 4328c2f713 Change default ReLU slope to .2 BREAKS COMPATIBILITY ... This conforms my ConvGnLelu implementation with the generally accepted negative_slope=.2. I have no idea where I got .1. This will break backwards compatibility with some older models but will likely improve their performance when freshly trained. I did some auditing to find what these models might be, and I am not actively using any of them, so probably OK.		2020-12-19 08:28:03 -07:00
..
byol	More refactor changes	2020-12-18 09:24:31 -07:00
fixup_resnet	More refactoring	2020-12-18 09:18:34 -07:00
flownet2@db2b7899ea	Update flownet submodule	2020-10-24 11:59:00 -06:00
glean	glean mods	2020-12-19 08:26:07 -07:00
srflow	More refactor changes	2020-12-18 09:24:31 -07:00
stylegan	GLEAN!	2020-12-18 16:04:19 -07:00
switched_conv@cb520afd4d	More refactoring	2020-12-18 09:18:34 -07:00
tecogan	More refactor changes	2020-12-18 09:24:31 -07:00
transformers	More refactoring	2020-12-18 09:18:34 -07:00
__init__.py	Lots of new discriminator nets	2020-11-10 16:06:54 -07:00
arch_util.py	Change default ReLU slope to .2 BREAKS COMPATIBILITY	2020-12-19 08:28:03 -07:00
discriminator_vgg_arch.py	More refactor changes	2020-12-18 09:24:31 -07:00
feature_arch.py	More refactoring	2020-12-18 09:18:34 -07:00
ProgressiveSrg_arch.py	More refactor changes	2020-12-18 09:24:31 -07:00
ResGen_arch.py	More refactoring	2020-12-18 09:18:34 -07:00
RRDBNet_arch.py	More refactor changes	2020-12-18 09:24:31 -07:00
spinenet_arch.py	More refactor changes	2020-12-18 09:24:31 -07:00
srg2_classic.py	More refactor changes	2020-12-18 09:24:31 -07:00
SwitchedResidualGenerator_arch.py	More refactor changes	2020-12-18 09:24:31 -07:00