RandAug preprocessing layer about keras-cv HOT 8 CLOSED

This will require rewriting from numpy to TensorFlow

I have been using this implementation. Maybe it can help:
https://github.com/tensorflow/models/blob/ded32f0500604928e52e27fd3f678e694e5133b7/official/vision/image_classification/augment.py#L905

from keras-cv.

This will require rewriting from numpy to TensorFlow

from keras-cv.

A batched implementation exists in imgaug:

https://github.com/aleju/imgaug

from keras-cv.

A batched implementation exists in imgaug:

https://github.com/aleju/imgaug

But it Is not the best solution as it needs to be tf.py_function wrapped as It handles Numpy arrays not Tensor.

from keras-cv.

I'll be contributing this shortly

from keras-cv.

If it could be to any inspiration, I also have a keras layer implementation of RandAug in my own toolbox:
https://github.com/chjort/chambers/tree/master/chambers/augmentations
specifically at this line.

It is based on https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/autoaugment.py, but my implementation includes vectorized/batched implementations of all transforms, although some of the layers make use of tensorflow-addons.

from keras-cv.

Thanks for the links! I’ll let you know if I used them. I’ll likely base mine on tensorflow similarity’s

from keras-cv.

https://github.com/tensorflow/similarity/blob/906d141b75acf00d0e1d37dd0d88c432bbb30f57/tensorflow_similarity/augmenters/img_augments.py

from keras-cv.