tfa.image.random_cutout

Apply cutout to images with random offset.

tfa.image.random_cutout(
    images: tfa.types.TensorLike,
    mask_size: tfa.types.TensorLike,
    constant_values: tfa.types.Number = 0,
    seed: tfa.types.Number = None
) -> tf.Tensor

This operation applies a (mask_height x mask_width) mask of zeros to a random location within images. The pixel values filled in will be of the value constant_values. The location where the mask will be applied is randomly chosen uniformly over the whole images.

Args
images	A tensor of shape (batch_size, height, width, channels) (NHWC).
mask_size	Specifies how big the zero mask that will be generated is that is applied to the images. The mask will be of size (mask_height x mask_width). Note: mask_size should be divisible by 2.
constant_values	What pixel value to fill in the images in the area that has the cutout mask applied to it.
seed	A Python integer. Used in combination with tf.random.set_seed to create a reproducible sequence of tensors across multiple calls.

Returns
A Tensor of the same shape and dtype as images.

Raises
InvalidArgumentError	if mask_size can't be divisible by 2.