o .wiQ@sddlmZddlmZmZmZmZddlmZddl m Z ddl m Z ddl mZddlmZddlmZmZes=d gZGd d d e Zd S) )Sequence)AnyListOptionalUnion)Tensor)relative_average_spectral_error)Metric) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE!RelativeAverageSpectralError.plotcseZdZUdZdZeed<dZeed<dZeed<dZ e ed<e e ed <e e ed < dd e d eeefddffdd Zd e d e ddfddZde fddZ ddeee ee fdeedefddZZS)RelativeAverageSpectralErrora+Computes Relative Average Spectral Error (RASE) (RelativeAverageSpectralError_). 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 - ``rase`` (:class:`~torch.Tensor`): returns float scalar tensor with average RASE value over sample Args: window_size: Sliding window used for rmse calculation kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Return: Relative Average Spectral Error (RASE) Example: >>> from torch import rand >>> preds = rand(4, 3, 16, 16) >>> target = rand(4, 3, 16, 16) >>> rase = RelativeAverageSpectralError() >>> rase(preds, target) tensor(5326.40...) Raises: ValueError: If ``window_size`` is not a positive integer. Fhigher_is_betterTis_differentiablefull_state_updategplot_lower_boundpredstarget window_sizekwargsreturnNc sftjdi|t|trt|tr|dkrtd|||_|jdgdd|jdgdddS)NzEArgument `window_size` is expected to be a positive integer, but got rcat)defaultdist_reduce_fxr)super__init__ isinstanceint ValueErrorr add_state)selfrr __class__rT/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/image/rase.pyr Fs z%RelativeAverageSpectralError.__init__cCs|j||j|dS)z*Update state with predictions and targets.N)rappendrr%rrrrr(updateTs z#RelativeAverageSpectralError.updatecCs"t|j}t|j}t|||jS)z/Compute Relative Average Spectral Error (RASE).)r rrrrr*rrr(computeYs  z$RelativeAverageSpectralError.computevalaxcCs |||S)aXPlot 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 RelativeAverageSpectralError >>> metric = RelativeAverageSpectralError() >>> metric.update(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torch import rand >>> from torchmetrics.image import RelativeAverageSpectralError >>> metric = RelativeAverageSpectralError() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(rand(4, 3, 16, 16), rand(4, 3, 16, 16))) >>> fig_, ax_ = metric.plot(values) )_plot)r%r-r.rrr(plot_s (r)r)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrr"dictstrrr r+r,rrrr r r0 __classcell__rrr&r(rs4        rN)collections.abcrtypingrrrrtorchr"torchmetrics.functional.image.rasertorchmetrics.metricr torchmetrics.utilities.datar torchmetrics.utilities.importsr torchmetrics.utilities.plotr r __doctest_skip__rrrrr(s