AntoineH/smart_augmentation: '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.

mirror of https://github.com/AntoineHX/smart_augmentation.git synced 2025-05-04 12:10:45 +02:00

'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

root f657a9f989 Final result brutus		2019-12-04 09:55:28 -05:00
FAR-HO	Initial Commit	2019-11-08 11:28:06 -05:00
Gradient-Descent-The-Ultimate-Optimizer	Initial Commit	2019-11-08 11:28:06 -05:00
higher	Final result brutus	2019-12-04 09:55:28 -05:00
PBA	Fix LeNet Tensorflow	2019-11-21 12:29:17 -05:00
UDA	Ajout RandAug (Before train) (Work in progress)	2019-12-02 06:38:13 -05:00
.gitignore	Ignore sample dir	2019-11-11 17:03:31 -05:00