a  d^@sddlmZmZmZmZmZddlmZddlm Z ddl m Z m Z ddl mZddlmZddlmZddlmZdd lmZmZesd gZGd d d eZd S))AnyListOptionalSequenceUnion)Tensor)Literal) _uqi_compute _uqi_update)Metric)rank_zero_warn) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEUniversalImageQualityIndex.plotcseZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e e ed <e e ed <deeee ededdfdd Ze e ddddZe dddZdeee ee feeedddZZS) UniversalImageQualityIndexaCompute Universal Image Quality Index (UniversalImageQualityIndex_). As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): Predictions from model of shape ``(N,C,H,W)`` - ``target`` (:class:`~torch.Tensor`): Ground truth values of shape ``(N,C,H,W)`` As output of `forward` and `compute` the metric returns the following output - ``uiqi`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average UIQI value over sample else returns tensor of shape ``(N,)`` with UIQI values per sample Args: kernel_size: size of the gaussian kernel sigma: Standard deviation of the gaussian kernel reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean (default) - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Return: Tensor with UniversalImageQualityIndex score Example: >>> import torch >>> from torchmetrics.image import UniversalImageQualityIndex >>> preds = torch.rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> uqi = UniversalImageQualityIndex() >>> uqi(preds, target) tensor(0.9216) Tis_differentiablehigher_is_betterFfull_state_updategplot_lower_boundg?plot_upper_boundpredstarget r?relementwise_mean)rsumnoneNN) kernel_sizesigma reductionkwargsreturnc sPtjfi|td|jdgdd|jdgdd||_||_||_dS)NzMetric `UniversalImageQualityIndex` will save all targets and predictions in buffer. For large datasets this may lead to large memory footprint.rcat)defaultZdist_reduce_fxr)super__init__r Z add_stater!r"r#)selfr!r"r#r$ __class___/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/image/uqi.pyr)Msz#UniversalImageQualityIndex.__init__)rrr%cCs*t||\}}|j||j|dS)z*Update state with predictions and targets.N)r rappendrr*rrr-r-r.updateas z!UniversalImageQualityIndex.update)r%cCs*t|j}t|j}t|||j|j|jS)z&Compute explained variance over state.)r rrr r!r"r#r0r-r-r.computegs  z"UniversalImageQualityIndex.compute)valaxr%cCs |||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 UniversalImageQualityIndex >>> preds = torch.rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> metric = UniversalImageQualityIndex() >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image import UniversalImageQualityIndex >>> preds = torch.rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> metric = UniversalImageQualityIndex() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )Z_plot)r*r3r4r-r-r.plotms,r)rrr)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrrrintrrr)r1r2rrrrr5 __classcell__r-r-r+r.rs2 %       rN)typingrrrrrZtorchrZtyping_extensionsrZ!torchmetrics.functional.image.uqir r Ztorchmetrics.metricr Ztorchmetrics.utilitiesr Ztorchmetrics.utilities.datar Ztorchmetrics.utilities.importsrZtorchmetrics.utilities.plotrrZ__doctest_skip__rr-r-r-r.s