AugMix layer
[source]
AugMix class
keras.layers.AugMix(
value_range=(0, 255),
num_chains=3,
chain_depth=3,
factor=0.3,
alpha=1.0,
all_ops=True,
interpolation="bilinear",
seed=None,
data_format=None,
**kwargs
)
Performs the AugMix data augmentation technique.
AugMix aims to produce images with variety while preserving the image
semantics and local statistics. During the augmentation process,
the same augmentation is applied across all images in the batch
in num_chains different ways, with each chain consisting of
chain_depth augmentations.
Arguments
- value_range: the range of values the incoming images will have.
Represented as a two number tuple written (low, high).
This is typically either
(0, 1) or (0, 255) depending
on how your preprocessing pipeline is set up.
- num_chains: an integer representing the number of different chains to
be mixed, defaults to 3.
- chain_depth: an integer representing the maximum number of
transformations to be applied in each chain. The actual number
of transformations in each chain will be sampled randomly
from the range
[0,chain_depth]. Defaults to 3.
- factor: The strength of the augmentation as a normalized value
between 0 and 1. Default is 0.3.
- alpha: a float value used as the probability coefficients for the
Beta and Dirichlet distributions, defaults to 1.0.
- all_ops: Use all operations (including random_brightness,
random_color_degeneration, random_contrast and random_sharpness).
Default is True.
- interpolation: The interpolation method to use for resizing operations.
Options include
"nearest", "bilinear". Default is "bilinear".
- seed: Integer. Used to create a random seed.
References