Closed JLrumberger closed 1 year ago
Non mixup part Without augmentations, with augmentations and with MixUp
In the promix paper they parameterize like this Beta(4.0,4.0), thus their actual \sigma \in [0.84, 1] which is used to weight image1 and image2 in MixUp. Honestly I don't see how MixUp improves results yet, qualitatively the images just look weird with it.
What is the purpose of this PR?
This PR closes #26 by adding the tf augmentation pipeline and mixup.
How did you implement your changes
Added classes
Flip
,Rot90
,GaussianNoise
,GaussianBlur
,Zoom
,LinearContrast
,MixUp
andAugmenter
. Augmenter applies augmentations on each image in a batch individually. MixUp works directly on batches, thus shouldn't be passed to Augmenter.Remaining issues
None