|View source on GitHub|
Apply cutout (https://arxiv.org/abs/1708.04552) to a video.
tfm.vision.augment.cutout_video( video: tf.Tensor, mask_shape: Optional[tf.Tensor] = None, replace: int = 0 ) -> tf.Tensor
This operation applies a random size 3D mask of zeros to a random location
video. The mask is padded The pixel values filled in will be of the
replace. The location where the mask will be applied is randomly
chosen uniformly over the whole video. If the size of the mask is not set,
then, it is randomly sampled uniformly from [0.25height, 0.5height],
[0.25width, 0.5width], and [1, 0.25*depth], which represent the height,
width, and number of frames of the input video tensor respectively.
|A video Tensor with cutout applied.|