Class CutOut

monai/transforms/regularization/array.py:169–199

Cutout as described in the paper: Terrance DeVries, Graham W. Taylor. Improved Regularization of Convolutional Neural Networks with Cutout, arXiv:1708.04552 Class derived from :py:class:`monai.transforms.Mixer`. See corresponding documentation for details on the constructor para

class CutOut(Mixer):
    """Cutout as described in the paper:
    Terrance DeVries, Graham W. Taylor.
    Improved Regularization of Convolutional Neural Networks with Cutout,
    arXiv:1708.04552

    Class derived from :py:class:`monai.transforms.Mixer`. See corresponding
    documentation for details on the constructor parameters. Here, alpha not only determines
    the mixing weight but also the size of the random rectangles being cut put.
    Please refer to the paper for details.
    """

    def apply(self, data: torch.Tensor):
        weights, _, coords = self._params
        nsamples, _, *dims = data.shape
        if len(weights) != nsamples:
            raise ValueError(f"Expected batch of size: {len(weights)}, but got {nsamples}")

        mask = torch.ones_like(data)
        for s, weight in enumerate(weights):
            lengths = [d * sqrt(1 - weight) for d in dims]
            idx = [slice(None)] + [slice(c, min(ceil(c + ln), d)) for c, ln, d in zip(coords, lengths, dims)]
            mask[s][idx] = 0

        return mask * data

    def __call__(self, data: torch.Tensor, randomize=True):
        data_t = convert_to_tensor(data, track_meta=get_track_meta())
        if randomize:
            self.randomize(data)
        return convert_to_dst_type(self.apply(data_t), dst=data)[0]