tf.keras.layers.ContrastLimitedAdaptiveHistogramEqualization

See Stable See Nightly

Contrast Limited Adaptive Histogram Equalization (CLAHE) layer.

Inherits From: Layer, Operation

tf.keras.layers.ContrastLimitedAdaptiveHistogramEqualization(
    value_range=(0, 255),
    clip_limit=4.0,
    tile_grid_size=(8, 8),
    data_format=None,
    **kwargs
)

CLAHE is a variant of Adaptive Histogram Equalization (AHE) which takes care of over-amplification of the contrast. It operates on small regions in the image, called tiles, rather than the entire image. The neighboring tiles are then combined using bilinear interpolation to remove the artificial boundaries. This algorithm can be applied to improve the contrast of an image.

Note: This layer computes histograms using self.backend.nn.one_hot, which can be highly memory-intensive. For large batch sizes or high-resolution images, it may lead to high memory consumption or out-of-memory errors.

Args
value_range	Optional list/tuple of 2 floats specifying the lower and upper limits of the input data values. Defaults to (0, 255).
clip_limit	Float. Limits the noise amplification in near-constant regions. Defaults to 4.0.
tile_grid_size	Tuple of 2 integers (height, width). Specifies the number of tiles to divide the image into. Defaults to (8, 8).
data_format	String, either "channels_last" or "channels_first". The ordering of the dimensions in the inputs. "channels_last" corresponds to inputs with shape (batch, height, width, channels) while "channels_first" corresponds to inputs with shape (batch, channels, height, width). It defaults to the image_data_format value found in your Keras config file at ~/.keras/keras.json. If you never set it, then it will be "channels_last".

Input shape
3D	unbatched) or 4D (batched) tensor with shape (..., height, width, channels), in "channels_last" format, or (..., channels, height, width), in "channels_first" format.

Output shape
3D	unbatched) or 4D (batched) tensor with shape (..., height, width, channels), or (..., channels, height, width), in "channels_first" format.

Example:

import keras
import numpy as np

# Create a CLAHE layer with default parameters
clahe = keras.layers.ContrastLimitedAdaptiveHistogramEqualization()

# Apply CLAHE to an image
# image values should be in the range[0, 255] by default
input_image = np.random.randint(0, 256, (1, 256, 256, 3))
output_image = clahe(input_image)

# For normalized images[0, 1]
clahe_normalized=keras.layers.ContrastLimitedAdaptiveHistogramEqualization(
    value_range=(0.0, 1.0)
)
norm_image = np.random.rand(1, 256, 256, 3)
output_norm = clahe_normalized(norm_image)

Attributes
input	Retrieves the input tensor(s) of a symbolic operation. Only returns the tensor(s) corresponding to the first time the operation was called.
output	Retrieves the output tensor(s) of a layer. Only returns the tensor(s) corresponding to the first time the operation was called.

Methods

convert_weight

View source

convert_weight(
    weight
)

Convert the weight if it is from the a different backend.

from_config

View source

@classmethod
from_config(
    config
)

Creates an operation from its config.

This method is the reverse of get_config, capable of instantiating the same operation from the config dictionary.

Note: If you override this method, you might receive a serialized dtype config, which is a dict. You can deserialize it as follows:

if "dtype" in config and isinstance(config["dtype"], dict):
    policy = dtype_policies.deserialize(config["dtype"])

Args
config	A Python dictionary, typically the output of get_config.

Returns
An operation instance.

get_random_transformation

View source

get_random_transformation(
    data, training=True, seed=None
)

transform_bounding_boxes

View source

transform_bounding_boxes(
    bounding_boxes, transformation, training=True
)

transform_images

View source

transform_images(
    images, transformation=None, training=True
)

transform_labels

View source

transform_labels(
    labels, transformation, training=True
)

transform_segmentation_masks

View source

transform_segmentation_masks(
    segmentation_masks, transformation, training=True
)

transform_single_bounding_box

View source

transform_single_bounding_box(
    bounding_box, transformation, training=True
)

transform_single_image

View source

transform_single_image(
    image, transformation, training=True
)

transform_single_label

View source

transform_single_label(
    label, transformation, training=True
)

transform_single_segmentation_mask

View source

transform_single_segmentation_mask(
    segmentation_mask, transformation, training=True
)