:j5ddlmZddlmZmZmZddlZddlmZddlm Z m Z ddl m Z ddl mZddlmZmZesd gZGd d e Zy) )Sequence)AnyOptionalUnionN)Tensor)_rmse_sw_compute_rmse_sw_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEz+RootMeanSquaredErrorUsingSlidingWindow.plotceZdZUdZdZeed<dZeed<dZeed<dZ e ed<e ed <d Z e e ed <e ed < dd edeeefdd ffd Zde de dd fdZde e fdZ dde ee ee fde edefdZxZS)&RootMeanSquaredErrorUsingSlidingWindowa@Computes Root Mean Squared Error (RMSE) using sliding window. 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 - ``rmse_sw`` (:class:`~torch.Tensor`): returns float scalar tensor with average RMSE-SW value over sample Args: window_size: Sliding window used for rmse calculation kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import rand >>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow >>> preds = rand(4, 3, 16, 16) >>> target = rand(4, 3, 16, 16) >>> rmse_sw = RootMeanSquaredErrorUsingSlidingWindow() >>> rmse_sw(preds, target) tensor(0.4158) Raises: ValueError: If ``window_size`` is not a positive integer. Fhigher_is_betterTis_differentiablefull_state_updateplot_lower_bound rmse_val_sumNrmse_map total_images window_sizekwargsreturnc .t|di|t|trt|tr|dkr t d||_|j dtjdd|j dtjddy) NzM 64++T->-> tO`O`? ;4=$*;r,c~|jJt|j|j|j\}}|S)zWCompute Root Mean Squared Error (using sliding window) and potentially return RMSE map.)rrrr)r)rmse_s r+computez.RootMeanSquaredErrorUsingSlidingWindow.compute\s9}}((("4#4#4dmmTEVEVWa r,valaxc&|j||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow >>> metric = RootMeanSquaredErrorUsingSlidingWindow() >>> metric.update(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow >>> metric = RootMeanSquaredErrorUsingSlidingWindow() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16))) >>> fig_, ax_ = metric.plot(values) )_plot)r)r:r;s r+plotz+RootMeanSquaredErrorUsingSlidingWindow.plotbsPzz#r""r,))NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrrr$dictstrrr"r5r9rrr r r> __classcell__)r*s@r+rrs:#d""t"#t#!e!!%Hhv% X XsCx. X  X F F t &)_c(#E&(6*:":;<(#IQRZI[(# (#r,r)collections.abcrtypingrrrr'r%torchmetrics.functional.image.rmse_swrr torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotr r __doctest_skip__rr r,r+rQs<%'' S&@@EFl#Vl#r,