forked from mrq/DL-Art-School
587a4f4050
I'm being really lazy here - these nets are not really different from each other except at which layer they terminate. This one terminates at 2x downsampling, which is simply indicative of a direction I want to go for testing these pixpro networks. |
||
|---|---|---|
| .. | ||
| byol | ||
| fixup_resnet | ||
| flownet2@db2b7899ea | ||
| glean | ||
| pixel_level_contrastive_learning | ||
| srflow | ||
| styled_sr | ||
| stylegan | ||
| tecogan | ||
| transformers | ||
| vqvae | ||
| __init__.py | ||
| arch_util.py | ||
| discriminator_vgg_arch.py | ||
| feature_arch.py | ||
| ResGen_arch.py | ||
| resnet_with_checkpointing.py | ||
| RRDBNet_arch.py | ||
| spinenet_arch.py | ||
| weighted_conv_resnet.py | ||