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 | ||
stylegan2 | ||
ui/image_labeler | ||
compute_fdpl_perceptual_weights.py | ||
create_lmdb.py | ||
extract_square_images.py | ||
extract_subimages_with_ref.py | ||
extract_subimages.py | ||
folderize_imagenet_val.py | ||
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 |