Alexandre Vicenzi 6c6e2ee6e4 Remove default loss function from generators ...

If the loss function is set as a default argument it will be loaded even
if not used, which is not desired.

FeatureLoss is used only for training, but was being loaded also for
inference, using a little more memory than required due VGG16 features.

This will not cause any harm because training and inference usage always
set gen_loss argument.

2019-10-28 23:27:51 +01:00

..

__init__.py

pypi: rename fasterai to deoldify

2019-08-20 21:22:00 +02:00

augs.py

code cleanup and refactor

2019-08-22 21:10:01 +02:00

critics.py

Refactor and cleanup

2019-10-19 14:31:49 +02:00

dataset.py

Refactor and cleanup

2019-10-19 14:31:49 +02:00

filters.py

Refactor and cleanup

2019-10-19 14:31:49 +02:00

generators.py

Remove default loss function from generators

2019-10-28 23:27:51 +01:00

layers.py

Refactor and cleanup

2019-10-19 14:31:49 +02:00

loss.py

Refactor and cleanup

2019-10-19 14:31:49 +02:00

save.py

code cleanup and refactor

2019-08-22 21:10:01 +02:00

unet.py

Refactor and cleanup

2019-10-19 14:31:49 +02:00

visualize.py

Refactor and cleanup

2019-10-19 14:31:49 +02:00