Keras 3 API documentation
Models API Layers API The base Layer class Layer activations Layer weight initializers Layer weight regularizers Layer weight constraints Core layers Convolution layers Pooling layers Recurrent layers Preprocessing layers Normalization layers Regularization layers Attention layers Reshaping layers Merging layers Activation layers Backend-specific layers Callbacks API Ops API Optimizers Metrics Losses Data loading Built-in small datasets Keras Applications Mixed precision Multi-device distribution RNG API Rematerialization Utilities
Keras 2 API documentation
► Keras 3 API documentation / Layers API / Preprocessing layers / Image augmentation layers / RandAugment layer

RandAugment layer

[source]

RandAugment class

keras.layers.RandAugment(
    value_range=(0, 255),
    num_ops=2,
    factor=0.5,
    interpolation="bilinear",
    seed=None,
    data_format=None,
    **kwargs
)

RandAugment performs the Rand Augment operation on input images.

This layer can be thought of as an all-in-one image augmentation layer. The policy implemented by this layer has been benchmarked extensively and is effective on a wide variety of datasets.

Note: This layer is safe to use inside a tf.data or grain pipeline (independently of which backend you're using).

References

Arguments

  • value_range: The range of values the input image can take. Default is (0, 255). Typically, this would be (0, 1) for normalized images or (0, 255) for raw images.
  • num_ops: The number of augmentation operations to apply sequentially to each image. Default is 2.
  • factor: The strength of the augmentation as a normalized value between 0 and 1. Default is 0.5.
  • interpolation: The interpolation method to use for resizing operations. Options include nearest, bilinear. Default is bilinear.
  • seed: Integer. Used to create a random seed.
RandAugment layer
RandAugment class