sAccuracy(num_classes=3, average=None), labels),
        ...     'multiclassrecall': ClasswiseWrapper(MulticlassRecall(num_classes=3, average=None), labels)}
        ... )
        >>> preds = torch.randn(10, 3).softmax(dim=-1)
        >>> target = torch.randint(3, (10,))
        >>> metric(preds, target)  # doctest: +NORMALIZE_WHITESPACE
        {'multiclassaccuracy_horse': tensor(0.),
         'multiclassaccuracy_fish': tensor(0.3333),
         'multiclassaccuracy_dog': tensor(0.4000),
         'multiclassrecall_horse': tensor(0.),
         'multiclassrecall_fish': tensor(0.3333),
         'multiclassrecall_dog': tensor(0.4000)}

    NÚ