407224eba1
Got rid of the converged multiplexer bases but kept the configurable architecture. The new multiplexers look a lot like the old one. Took some queues from the transformer architecture: translate image to a higher filter-space and stay there for the duration of the models computation. Also perform convs after each switch to allow the model to anneal issues that arise. |
||
---|---|---|
.. | ||
__init__.py | ||
arch_util.py | ||
AttentionResnet.py | ||
discriminator_vgg_arch.py | ||
DiscriminatorResnet_arch_passthrough.py | ||
DiscriminatorResnet_arch.py | ||
feature_arch.py | ||
FlatProcessorNet_arch.py | ||
FlatProcessorNetNew_arch.py | ||
HighToLowResNet.py | ||
ResGen_arch.py | ||
RRDBNet_arch.py | ||
SRResNet_arch.py | ||
SwitchedResidualGenerator_arch.py |