forked from ecker/DL-Art-School
- Just use resnet blocks for the multiplexer trunk of the generator - Every block initializes itself, rather than everything at the end - Cleans up some messy parts of the architecture, including unnecessary kernel sizes and places where BN is not used properly. |
||
|---|---|---|
| .. | ||
| __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 | ||
| NestedSwitchGenerator.py | ||
| ResGen_arch.py | ||
| RRDBNet_arch.py | ||
| SRResNet_arch.py | ||
| SwitchedResidualGenerator_arch.py | ||