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 / Solarization layer

Solarization layer

[source]

Solarization class

keras.layers.Solarization(
    addition_factor=0.0, threshold_factor=0.0, value_range=(0, 255), seed=None, **kwargs
)

Applies (max_value - pixel + min_value) for each pixel in the image.

When created without threshold parameter, the layer performs solarization to all values. When created with specified threshold the layer only augments pixels that are above the threshold value.

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

Arguments

  • addition_factor: (Optional) A tuple of two floats or a single float, between 0 and 1. For each augmented image a value is sampled from the provided range. If a float is passed, the range is interpreted as (0, addition_factor). If specified, this value (times the value range of input images, e.g. 255), is added to each pixel before solarization and thresholding. Defaults to 0.0.
  • threshold_factor: (Optional) A tuple of two floats or a single float. For each augmented image a value is sampled from the provided range. If a float is passed, the range is interpreted as (0, threshold_factor). If specified, only pixel values above this threshold will be solarized.
  • value_range: a tuple or a list of two elements. The first value represents the lower bound for values in input images, the second represents the upper bound. Images passed to the layer should have values within value_range. Typical values to pass are (0, 255) (RGB image) or (0., 1.) (scaled image).
  • seed: Integer. Used to create a random seed.
  • **kwargs: Base layer keyword arguments, such as name and dtype.

Example

(images, labels), _ = keras.datasets.cifar10.load_data()
print(images[0, 0, 0])
# [59 62 63]
# Note that images are Tensor with values in the range [0, 255]
solarization = Solarization(value_range=(0, 255))
images = solarization(images)
print(images[0, 0, 0])
# [196, 193, 192]
Solarization layer
Solarization class