James Betker d1007ccfe7 Adjustments to pixpro to allow training against networks with arbitrarily large structural latents ... - 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.		2021-01-12 09:17:45 -07:00
..
byol	Support training imagenet classifier	2021-01-11 20:09:16 -07:00
stylegan2
ui/image_labeler
compute_fdpl_perceptual_weights.py
create_lmdb.py
extract_square_images.py	Adjustments to pixpro to allow training against networks with arbitrarily large structural latents	2021-01-12 09:17:45 -07:00
extract_subimages_with_ref.py	Add lucidrains pixpro trainer	2021-01-05 20:14:22 -07:00
extract_subimages.py
folderize_imagenet_val.py	Support training imagenet classifier	2021-01-11 20:09:16 -07:00
recover_tensorboard_log.py
rename.py
srflow_latent_space_playground.py
test_psnr_approximator.py
use_discriminator_as_filter.py
use_generator_as_filter.py
validate_data.py