i]ddlmZmZmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z mZddlmZmZe sdgZesd dgZGd d e Zy) )AnyLiteralOptionalSequenceUnionN)Tensor) _dists_update)Metric)_MATPLOTLIB_AVAILABLE_TORCHVISION_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEz+DeepImageStructureAndTextureSimilarity.plot&DeepImageStructureAndTextureSimilarityceZdZUdZeed<eed<dZeed<dZeed<dZ eed<d Z e ed <dd e e d d eddffd ZdededdfdZdefdZ dde eeeefde edefdZxZS)raCalculates Deep Image Structure and Texture Similarity (DISTS) score. The metric is a full-reference image quality assessment (IQA) model that combines sensitivity to structural distortions (e.g., artifacts due to noise, blur, or compression) with a tolerance of texture resampling (exchanging the content of a texture region with a new sample of the same texture). The metric is based on a convolutional neural network (CNN) that transforms the reference and distorted images to a new representation. Within this representation, a set of measurements are developed that are sufficient to capture the appearance of a variety of different visual distortions. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): tensor with images of shape ``(N, 3, H, W)`` - ``target`` (:class:`~torch.Tensor`): tensor with images of shape ``(N, 3, H, W)`` As output of `forward` and `compute` the metric returns the following output - ``lpips`` (:class:`~torch.Tensor`): returns float scalar tensor with average LPIPS value over samples Args: reduction: specifies the reduction to apply to the output. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If `reduction` is not one of ["mean", "sum"] Example: >>> from torch import rand >>> from torchmetrics.image.dists import DeepImageStructureAndTextureSimilarity >>> metric = DeepImageStructureAndTextureSimilarity() >>> preds = rand(10, 3, 100, 100) >>> target = rand(10, 3, 100, 100) >>> metric(preds, target) tensor(0.1882, grad_fn=) scoretotalTis_differentiableFhigher_is_betterfull_state_updateplot_lower_bound reductionmeansumkwargsreturnNc t|d i|d}||vrtd|d|||_|j dt j dd|j dt j ddy) Nrz+Argument `reduction` expected to be one of z but got rrr)defaultdist_reduce_fxr)super__init__ ValueErrorr add_statetorchtensor)selfrrallowed_reductions __class__s m/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/image/dists.pyr#z/DeepImageStructureAndTextureSimilarity.__init__Ms} "6", . .JK]J^^ghqgrst t" w S(9%P w S(9%Ppredstargetct||}|xj|jz c_|xj|jdz c_y)zUpdate the metric state.rN)r rrrshape)r(r-r.scoress r+updatez-DeepImageStructureAndTextureSimilarity.updateVs8uf- fjjl"  ekk!n$ r,cj|jdk(r|j|jz S|jS)zComputes the DISTS score.r)rrr)r(s r+computez.DeepImageStructureAndTextureSimilarity.compute\s)*...F*BtzzDJJ&R Rr,valaxc&|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.dists import DeepImageStructureAndTextureSimilarity >>> metric = DeepImageStructureAndTextureSimilarity() >>> metric.update(torch.rand(10, 3, 100, 100), torch.rand(10, 3, 100, 100)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image.dists import DeepImageStructureAndTextureSimilarity >>> metric = DeepImageStructureAndTextureSimilarity() >>> values = [ ] >>> for _ in range(3): ... values.append(metric(torch.rand(10, 3, 100, 100), torch.rand(10, 3, 100, 100))) >>> fig_, ax_ = metric.plot(values) )_plot)r(r5r6s r+plotz+DeepImageStructureAndTextureSimilarity.plot`sPzz#r""r,)r)NN)__name__ __module__ __qualname____doc__r__annotations__rboolrrrfloatrrrr#r2r4rrr rr9 __classcell__)r*s@r+rrs#J M M"t""d"#t#!e!Q(7=+A"BQWZQ_cQ%F%F%t% SS _c(#E&(6*:":;<(#IQRZI[(# (#r,)typingrrrrrr&r#torchmetrics.functional.image.distsr torchmetrics.metricr torchmetrics.utilities.importsr r torchmetrics.utilities.plotr r__doctest_skip__rr!r,r+rHsH;: =&X@EF@Bopi#Vi#r,