forked from mrq/DL-Art-School
aa0305def9
It's been a tough day figuring out WTH is going on with my discriminators. It appears the raw FixUp discriminator can get into an "defective" state where they stop trying to learn and just predict as close to "0" D_fake and D_real as possible. In this state they provide no feedback to the generator and never recover. Adding batch norm back in seems to fix this so it must be some sort of parameterization error.. Should look into fixing this in the future. |
||
|---|---|---|
| .. | ||
| dcn | ||
| __init__.py | ||
| arch_util.py | ||
| discriminator_vgg_arch.py | ||
| DiscriminatorResnet_arch_passthrough.py | ||
| DiscriminatorResnet_arch.py | ||
| DUF_arch.py | ||
| EDVR_arch.py | ||
| FlatProcessorNet_arch.py | ||
| FlatProcessorNetNew_arch.py | ||
| HighToLowResNet.py | ||
| ResGen_arch.py | ||
| RRDBNet_arch.py | ||
| RRDBNetXL_arch.py | ||
| SRResNet_arch.py | ||
| TOF_arch.py | ||