tf.keras.layers.RandomGrayscale

See Stable See Nightly

Preprocessing layer for random conversion of RGB images to grayscale.

Inherits From: Layer, Operation

tf.keras.layers.RandomGrayscale(
    factor=0.5, data_format=None, seed=None, **kwargs
)

This layer randomly converts input images to grayscale with a specified
factor. When applied, it maintains the original number of channels
but sets all channels to the same grayscale value. This can be useful
for data augmentation and training models to be robust to color
variations.

The conversion preserves the perceived luminance of the original color
image using standard RGB to grayscale conversion coefficients. Images
that are not selected for conversion remain unchanged.

Note: This layer is safe to use inside a <a href="../../../tf/data"><code>tf.data</code></a> or `grain` pipeline
(independently of which backend you're using).

Args:
    factor: Float between 0 and 1, specifying the factor of
        converting each image to grayscale. Defaults to 0.5. A value of
        1.0 means all images will be converted, while 0.0 means no images
        will be converted.
    data_format: String, one of `"channels_last"` (default) 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)`.

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:
    Same as input shape. The output maintains the same number of channels
    as the input, even for grayscale-converted images where all channels
    will have the same value.

Example:

layer = keras.layers.RandomGrayscale(value_range=(0, 255))
images = np.random.randint(0, 255, (8, 224, 224, 3), dtype="uint8")

labels = keras.ops.one_hot(
    np.array([0, 1, 2, 0, 1, 2, 0, 1]),
    num_classes=3
)

segmentation_masks = np.random.randint(0, 3, (8, 224, 224, 1), dtype="uint8")

output = layer(
    {
        "images": images,
        "labels": labels,
        "segmentation_masks": segmentation_masks
    },
    training=True
)

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(
    images, training=True, seed=None
)

transform_bounding_boxes

View source

transform_bounding_boxes(
    bounding_boxes, **kwargs
)

transform_images

View source

transform_images(
    images, transformation, training=True
)

transform_labels

View source

transform_labels(
    labels, transformations=None, **kwargs
)

transform_segmentation_masks

View source

transform_segmentation_masks(
    segmentation_masks, transformations=None, **kwargs
)

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
)