a  d @sddlmZmZmZddlmZddlmZeeeefdddZ eeeefeededd d Z deeeded d dZ dS))OptionalTupleUnion)Tensor)Literal)imgreturncCs|jdkrtd|j|dddddf|dddddf}|dddddf|dddddf}|gd}|gd}||}||jdfS) z4Compute total variation statistics on current batch.z1Expected input `img` to be an 4D tensor, but got .N)r r)ndim RuntimeErrorshapeabssum)rZdiff1Zdiff2Zres1Zres2scoreri/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/functional/image/tv.py_total_variation_updates ,,r)meanrnone)r num_elements reductionrcCsD|dkr||S|dkr$|S|dus4|dkr8|StddS)z$Compute final total variation score.rrNrzHExpected argument `reduction` to either be 'sum', 'mean', 'none' or None)r ValueError)rrrrrr_total_variation_compute!s rr)rrrcCst|\}}t|||S)a[Compute 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.image 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) typingrrrZtorchrZtyping_extensionsrintrrrrrrrs