tfm.vision.augment.cutout_video

Apply cutout (https://arxiv.org/abs/1708.04552) to a video.

This operation applies a random size 3D mask of zeros to a random location within video. The mask is padded The pixel values filled in will be of the value 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.

video A video Tensor of shape [T, H, W, C].
mask_shape An optional integer tensor that specifies the depth, height and width of the mask to cut. If it is not set, the shape is randomly sampled as described above. The shape dimensions should be divisible by 2 otherwise they will rounded down.
replace What pixel value to fill in the image in the area that has the cutout mask applied to it.

A video Tensor with cutout applied.