a  d@sddlmZmZmZmZmZddlmZddlm Z ddl m Z m Z ddl mZddlmZddlmZddlmZdd lmZmZesd gZGd d d eZd S))AnyListOptionalSequenceUnion)Tensor)Literal)"_spectral_distortion_index_compute!_spectral_distortion_index_update)Metric)rank_zero_warn) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPESpectralDistortionIndex.plotcseZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e e ed <e e ed <deededdfdd Ze e ddddZe dddZdeee ee feeedddZZS)SpectralDistortionIndexaCompute Spectral Distortion Index (SpectralDistortionIndex_) also now as D_lambda. The metric is used to compare the spectral distortion between two images. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): Low resolution multispectral image of shape ``(N,C,H,W)`` - ``target``(:class:`~torch.Tensor`): High resolution fused image of shape ``(N,C,H,W)`` 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 SDI value over sample else returns tensor of shape ``(N,)`` with SDI values per sample Args: p: Large spectral differences reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean (default) - ``'sum'``: takes the sum - ``'none'``: no reduction will be applied kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> import torch >>> _ = torch.manual_seed(42) >>> from torchmetrics.image import SpectralDistortionIndex >>> preds = torch.rand([16, 3, 16, 16]) >>> target = torch.rand([16, 3, 16, 16]) >>> sdi = SpectralDistortionIndex() >>> sdi(preds, target) tensor(0.0234) Thigher_is_betteris_differentiableFfull_state_updategplot_lower_boundg?plot_upper_boundpredstargetelementwise_meanrsumnoneN)p reductionkwargsreturnc stjfi|tdt|tr,|dkr>> # Example plotting a single value >>> import torch >>> _ = torch.manual_seed(42) >>> from torchmetrics.image import SpectralDistortionIndex >>> preds = torch.rand([16, 3, 16, 16]) >>> target = torch.rand([16, 3, 16, 16]) >>> metric = SpectralDistortionIndex() >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> _ = torch.manual_seed(42) >>> from torchmetrics.image import SpectralDistortionIndex >>> preds = torch.rand([16, 3, 16, 16]) >>> target = torch.rand([16, 3, 16, 16]) >>> metric = SpectralDistortionIndex() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )Z_plot)r+r4r5r.r.r/plotls.r)rr)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrrr)rrr'r2r3rrrrrr6 __classcell__r.r.r,r/rs( $        rN)typingrrrrrZtorchrZtyping_extensionsrZ&torchmetrics.functional.image.d_lambdar r Ztorchmetrics.metricr Ztorchmetrics.utilitiesr Ztorchmetrics.utilities.datar Ztorchmetrics.utilities.importsrZtorchmetrics.utilities.plotrrZ__doctest_skip__rr.r.r.r/s