d1007ccfe7
- The pixpro latent now rescales the latent space instead of using a "coordinate vector", which **might** have performance implications. - The latent against which the pixel loss is computed can now be a small, randomly sampled patch out of the entire latent, allowing further memory/computational discounts. Since the loss computation does not have a receptive field, this should not alter the loss. - The instance projection size can now be separate from the pixel projection size. - PixContrast removed entirely. - ResUnet with full resolution added. |
||
---|---|---|
.. | ||
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 |