:jddlmZddlmZmZmZmZddlZddlmZm Z ddl m Z ddl m Z mZddlmZddlmZdd lmZdd lmZmZesd gZGd d eZy))Sequence)AnyListOptionalUnionN)Tensortensor)Literal)_total_variation_compute_total_variation_update)Metric) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzTotalVariation.plotceZdZUdZdZeed<dZeed<dZeed<dZ e ed<e ed <e e ed <e ed <dd e ed deddffd Zde ddfdZde fdZ dde ee ee fde edefdZxZS)TotalVariationaCompute Total Variation loss (`TV`_). As input to ``forward`` and ``update`` the metric accepts the following input - ``img`` (:class:`~torch.Tensor`): A tensor of shape ``(N, C, H, W)`` consisting of images As output of `forward` and `compute` the metric returns the following output - ``sdi`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average TV value over sample else returns tensor of shape ``(N,)`` with TV values per sample Args: 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 kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If ``reduction`` is not one of ``'sum'``, ``'mean'``, ``'none'`` or ``None`` Example: >>> from torch import rand >>> from torchmetrics.image import TotalVariation >>> tv = TotalVariation() >>> img = torch.rand(5, 3, 28, 28) >>> tv(img) tensor(7546.8018) Ffull_state_updateTis_differentiablehigher_is_bettergplot_lower_bound num_elements score_listscore reduction)meansumnonekwargsreturnNc 0t|d i|||dvr td||_|j dgd|j dt dt jd |j d t dt jd y) N)rrrzHExpected argument `reduction` to either be 'sum', 'mean', 'none' or Nonercat)defaultdist_reduce_fxrr)dtyperr) super__init__ ValueErrorr add_stater torchfloatint)selfrr __class__s j/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/image/tv.pyr(zTotalVariation.__init__Ks "6"  Y6M%Mgh h" |RF wq (DUZ[ ~vauyy/IZ_`imgct|\}}|j|jdk(r|jj|n#|xj|j z c_|xj |z c_y)z0Update current score with batch of input images.Nr)r rrappendrrr)r.r2rrs r0updatezTotalVariation.updateUs]5c:| >> !T^^v%= OO " "5 ) JJ%))+ %J \)r1c|j|jdk(rt|jn |j}t ||j |jS)zCompute final total variation.r)rrrrr r)r.rs r0computezTotalVariation.compute^sG151G4>>]cKc T__-imisis't/@/@$..QQr1valaxc&|j||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.image import TotalVariation >>> metric = TotalVariation() >>> metric.update(torch.rand(5, 3, 28, 28)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image import TotalVariation >>> metric = TotalVariation() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(5, 3, 28, 28))) >>> fig_, ax_ = metric.plot(values) )_plot)r.r8r9s r0plotzTotalVariation.plotcsPzz#r""r1)r)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrr,rrrr rr(r5r7rrrrr< __classcell__)r/s@r0rrs D$t#"t""d"!e!V  Ma(73H+I"Ja^aafja*&*T*RR _c(#E&(6*:":;<(#IQRZI[(# (#r1r)collections.abcrtypingrrrrr+rr typing_extensionsr torchmetrics.functional.image.tvr r torchmetrics.metricr torchmetrics.utilities.datartorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr&r1r0rMsB%-- %^&4@@-.l#Vl#r1