o yi @s|ddlmZddlmZddlmZdedeeeffddZded ed ed defd d Zdded ed defddZ dS))Tuple)Tensor)LiteralimgreturncCs|jdkr td|j|dddddf|dddddf}|dddddf|dddddf}|gd}|gd}||}||jdfS) z5Computes total variation statistics on current batch.z1Expected input `img` to be an 4D tensor, but got .N)rr)ndim RuntimeErrorshapeabssum)rdiff1diff2res1res2scorerT/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/image/tv.py_total_variation_updates ,,rr num_elements reduction)meanrnoneNcCs@|dkr ||S|dkr|S|dus|dkr|Std)z$Compute final total variation score.rrNrzHExpected argument `reduction` to either be 'sum', 'mean', 'none' or None)r ValueError)rrrrrr_total_variation_compute!s rrcCst|\}}t|||S)aUComputes total variation loss. Args: img: A `Tensor` of shape `(N, C, H, W)` consisting of images reduction: a method to reduce metric score over samples. - ``'mean'``: takes the mean over samples - ``'sum'``: takes the sum over samples - ``None`` or ``'none'``: return the score per sample Returns: A loss scalar value containing the total variation Raises: ValueError: If ``reduction`` is not one of ``'sum'``, ``'mean'``, ``'none'`` or ``None`` RuntimeError: If ``img`` is not 4D tensor Example: >>> import torch >>> from torchmetrics.functional import total_variation >>> _ = torch.manual_seed(42) >>> img = torch.rand(5, 3, 28, 28) >>> total_variation(img) tensor(7546.8018) )rr)rrrrrrrtotal_variation/s  rN)r) typingrtorchrtyping_extensionsrintrrrrrrrs