'Smart_aug' objective is to make data augmentation differentiable, thus allowing to learn its parameters, with 'Higher' objects, such as 'Data_aug' classes. The meta-learning of the data augmentation parameter is performed jointly with the training of the model. Thus it minimize the overhead compared to other data augmentation learning techniques.
Find a file
2020-01-13 12:19:25 -05:00
FAR-HO Changement permission fichiers + Simplification utilisation Augmented_dataset 2019-12-04 14:48:11 -05:00
Gradient-Descent-The-Ultimate-Optimizer Changement permission fichiers + Simplification utilisation Augmented_dataset 2019-12-04 14:48:11 -05:00
higher MaJ des ignore mag pour la regularization 2020-01-13 12:19:25 -05:00
PBA Changement permission fichiers + Simplification utilisation Augmented_dataset 2019-12-04 14:48:11 -05:00
salvador Salvador tests 2019-12-12 16:38:13 -05:00
UDA Changement permission fichiers + Simplification utilisation Augmented_dataset 2019-12-04 14:48:11 -05:00
.gitignore Changement permission fichiers + Simplification utilisation Augmented_dataset 2019-12-04 14:48:11 -05:00