tf.keras.layers.RandomGaussianBlur

tf.keras.layers.RandomGaussianBlur(
    factor=1.0,
    kernel_size=3,
    sigma=1.0,
    value_range=(0, 255),
    data_format=None,
    seed=None,
    **kwargs
)

This layer performs a Gaussian blur operation on input images with a
randomly selected degree of blurring, controlled by the `factor` and
`sigma` arguments.

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: A single float or a tuple of two floats.
        `factor` controls the extent to which the image hue is impacted.
        `factor=0.0` makes this layer perform a no-op operation,
        while a value of `1.0` performs the most aggressive
        blurring available. If a tuple is used, a `factor` is
        sampled between the two values for every image augmented. If a
        single float is used, a value between `0.0` and the passed float is
        sampled. Default is 1.0.
    kernel_size: Integer. Size of the Gaussian kernel used for blurring.
        Must be an odd integer. Default is 3.
    sigma: Float or tuple of two floats. Standard deviation of the Gaussian
        kernel. Controls the intensity of the blur. If a tuple is provided,
        a value is sampled between the two for each image. Default is 1.0.
    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.
    seed: Integer. Used to create a random seed.

Example:

layer = keras.layers.RandomGaussianBlur(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
)

convert_weight(
    weight
)

@classmethod
from_config(
    config
)

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

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

transform_bounding_boxes(
    bounding_boxes, transformation, training=True
)

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

transform_labels(
    labels, transformation, training=True
)

transform_segmentation_masks(
    segmentation_masks, transformation, training=True
)

transform_single_bounding_box(
    bounding_box, transformation, training=True
)

transform_single_image(
    image, transformation, training=True
)

transform_single_label(
    label, transformation, training=True
)

transform_single_segmentation_mask(
    segmentation_mask, transformation, training=True
)