o .wi`@sddlmZddlmZmZmZmZddlmZddl m Z ddl m Z m Z ddlmZddlmZddlmZdd lmZdd lmZmZesKd gZGd d d eZdS))Sequence)AnyListOptionalUnion)Tensor)Literal)_ergas_compute _ergas_update)Metric)rank_zero_warn) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE.ErrorRelativeGlobalDimensionlessSynthesis.plotc seZdZUdZdZeed<dZeed<dZeed<dZ e ed<e e ed <e e ed < dd e de ddeddffdd Zd e d e ddfddZde fddZ ddeee ee fdeedefddZZS))ErrorRelativeGlobalDimensionlessSynthesisaCalculate the `Error relative global dimensionless synthesis`_ (ERGAS) metric. This metric is used to calculate the accuracy of Pan sharpened image considering normalized average error of each band of the result image. It is defined as: .. math:: ERGAS = \frac{100}{r} \cdot \sqrt{\frac{1}{N} \sum_{k=1}^{N} \frac{RMSE(B_k)^2}{\mu_k^2}} where :math:`r=h/l` denote the ratio in spatial resolution (pixel size) between the high and low resolution images. :math:`N` is the number of spectral bands, :math:`RMSE(B_k)` is the root mean square error of the k-th band between low and high resolution images, and :math:`\\mu_k` is the mean value of the k-th band of the reference image. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): Predictions from model - ``target`` (:class:`~torch.Tensor`): Ground truth values As output of `forward` and `compute` the metric returns the following output - ``ergas`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average ERGAS value over sample else returns tensor of shape ``(N,)`` with ERGAS values per sample Args: ratio: ratio of high resolution to low resolution. 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. Example: >>> from torch import rand >>> from torchmetrics.image import ErrorRelativeGlobalDimensionlessSynthesis >>> preds = rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> ergas = ErrorRelativeGlobalDimensionlessSynthesis() >>> ergas(preds, target).round() tensor(10.) Fhigher_is_betterTis_differentiablefull_state_updategplot_lower_boundpredstargetelementwise_meanratio reduction)rsumnoneNkwargsreturnNc sJtjdi|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)defaultdist_reduce_fxr)super__init__r add_staterr)selfrrr __class__r$U/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/image/ergas.pyr&Ts z2ErrorRelativeGlobalDimensionlessSynthesis.__init__cCs*t||\}}|j||j|dS)z*Update state with predictions and targets.N)r rappendrr(rrr$r$r+updatefs z0ErrorRelativeGlobalDimensionlessSynthesis.updatecCs&t|j}t|j}t|||j|jS)z&Compute explained variance over state.)r rrr rrr-r$r$r+computels  z1ErrorRelativeGlobalDimensionlessSynthesis.computevalaxcCs |||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> from torch import rand >>> from torchmetrics.image import ErrorRelativeGlobalDimensionlessSynthesis >>> preds = rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> metric = ErrorRelativeGlobalDimensionlessSynthesis() >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torch import rand >>> from torchmetrics.image import ErrorRelativeGlobalDimensionlessSynthesis >>> preds = rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> metric = ErrorRelativeGlobalDimensionlessSynthesis() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )_plot)r(r0r1r$r$r+plotrs ,r)rr)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrrrr&r.r/rrrrrr3 __classcell__r$r$r)r+r s:  +     rN)collections.abcrtypingrrrrtorchrtyping_extensionsr#torchmetrics.functional.image.ergasr r torchmetrics.metricr torchmetrics.utilitiesr torchmetrics.utilities.datar torchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr$r$r$r+s