tf.keras.layers.RandomPerspective

tf.keras.layers.RandomPerspective(
    factor=1.0,
    scale=1.0,
    interpolation='bilinear',
    fill_value=0.0,
    seed=None,
    data_format=None,
    **kwargs
)

This layer distorts the perspective of input images by shifting their
corner points, simulating a 3D-like transformation. The amount of distortion
is controlled by the `factor` and `scale` parameters.

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 float or a tuple of two floats.
        Represents the probability of applying the perspective
        transformation to each image in the batch.

        - `factor=0.0` ensures no transformation is applied.
        - `factor=1.0` means the transformation is always applied.
        - If a tuple `(min, max)` is provided, a probability is randomly
          sampled between `min` and `max` for each image.
        - If a single float is given, the probability is sampled between
          `0.0` and the provided float.
        Default is 1.0.
    scale: A float defining the relative amount of perspective shift.
        Determines how much the image corners are displaced, affecting
        the intensity of the perspective effect.
    interpolation: Interpolation mode. Supported values: `"nearest"`,
        `"bilinear"`.
    fill_value: a float represents the value to be filled outside the
        boundaries when `fill_mode="constant"`.
    seed: Integer. Used to create a random seed.

Example:

layer = keras.layers.RandomPerspective(bounding_box_format="xyxy")
images = np.random.randint(0, 255, (4, 224, 224, 3), dtype="uint8")

bounding_boxes = {
    "boxes": np.array([
        [[10, 20, 100, 150], [50, 60, 200, 250]],
        [[15, 25, 110, 160], [55, 65, 210, 260]],
        [[20, 30, 120, 170], [60, 70, 220, 270]],
        [[25, 35, 130, 180], [65, 75, 230, 280]],
    ], dtype="float32"),
    "labels": np.array([[0, 1], [1, 2], [2, 3], [0, 3]], dtype="int32")
}

labels = keras.ops.one_hot(
    np.array([0, 1, 2, 3]),
    num_classes=4
)

segmentation_masks = np.random.randint(0, 3, (4, 224, 224, 1), dtype="uint8")

output = layer(
    {
        "images": images,
        "bounding_boxes": bounding_boxes,
        "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, 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
)