Mixup

Mixup is a data augmentation technique that generates new training samples by linearly interpolating pairs of images. We follow the implementation of mixup in SRe2L.

CLASS
dd_ranking.aug.Mixup(params: dict)
[SOURCE]

Parameters

params(dict): Parameters for the mixup augmentation. We require the parameters to be in the format of {'param_name': param_value}. For mixup, only lambda (mixup strength) needs to be specified, e.g. {'lambda': 0.8}.

Example

# When intializing an evaluator with mixup augmentation, and mixup object will be constructed.
>>> self.aug_func = Mixup(params={'lambda': 0.8})

# During training, the mixup object will be used to augment the data.
>>> images = aug_func(images)