forked from mrq/DL-Art-School
dc17545083
Allows downsampling immediately before processing, which reduces network complexity on higher resolution images but keeps a higher filter count. |
||
---|---|---|
.. | ||
__init__.py | ||
arch_util.py | ||
AttentionResnet.py | ||
biggan_gen_arch.py | ||
biggan_layers.py | ||
biggan_sync_batchnorm.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 |