:jsddlmZddlmZmZmZmZddlmZddl m Z ddl m Z m Z ddlmZddlmZddlmZdd lmZmZesd gZGd d eZy ))Sequence)AnyListOptionalUnion)Tensor)Literal)_cosine_similarity_compute_cosine_similarity_update)Metric) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzCosineSimilarity.plotceZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e e ed <e e ed < dd eddeddffd Zd e d e ddfdZde fdZ ddeee ee fdeedefdZxZS)CosineSimilarityaCompute the `Cosine Similarity`_. .. math:: cos_{sim}(x,y) = \frac{x \cdot y}{||x|| \cdot ||y||} = \frac{\sum_{i=1}^n x_i y_i}{\sqrt{\sum_{i=1}^n x_i^2}\sqrt{\sum_{i=1}^n y_i^2}} where :math:`y` is a tensor of target values, and :math:`x` is a tensor of predictions. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): Predicted float tensor with shape ``(N,d)`` - ``target`` (:class:`~torch.Tensor`): Ground truth float tensor with shape ``(N,d)`` As output of ``forward`` and ``compute`` the metric returns the following output: - ``cosine_similarity`` (:class:`~torch.Tensor`): A float tensor with the cosine similarity Args: reduction: how to reduce over the batch dimension using 'sum', 'mean' or 'none' (taking the individual scores) kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import tensor >>> from torchmetrics.regression import CosineSimilarity >>> target = tensor([[0, 1], [1, 1]]) >>> preds = tensor([[0, 1], [0, 1]]) >>> cosine_similarity = CosineSimilarity(reduction = 'mean') >>> cosine_similarity(preds, target) tensor(0.8536) Tis_differentiablehigher_is_betterFfull_state_updategplot_lower_boundg?plot_upper_boundpredstarget reduction)meansumnoneNkwargsreturnNc t|di|d}||vrtd|d|||_|j dgd|j dgdy) N)rrrNz+Expected argument `reduction` to be one of z but got rcat)dist_reduce_fxr)super__init__ ValueErrorr add_state)selfrrallowed_reduction __class__s ~/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/regression/cosine_similarity.pyr%zCosineSimilarity.__init__Hsm "6"9 - -JK\J]]fgpfqrs s" w59 xE:ct||\}}|jj||jj|y)z2Update metric states with predictions and targets.N)r rappendrr(rrs r+updatezCosineSimilarity.updateVs61%@ v %  6"r,ct|j}t|j}t|||jS)zCompute metric.)r rrr rr/s r+computezCosineSimilarity.compute]s1TZZ(dkk*)%HHr,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 >>> from torch import randn >>> # Example plotting a single value >>> from torchmetrics.regression import CosineSimilarity >>> metric = CosineSimilarity() >>> metric.update(randn(10,2), randn(10,2)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import randn >>> # Example plotting multiple values >>> from torchmetrics.regression import CosineSimilarity >>> metric = CosineSimilarity() >>> values = [] >>> for _ in range(10): ... values.append(metric(randn(10,2), randn(10,2))) >>> fig, ax = metric.plot(values) )_plot)r(r3r4s r+plotzCosineSimilarity.plotcsPzz#r""r,)r)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrrr rr%r0r2rrrrrr7 __classcell__)r*s@r+rrs@#t"!d!#t#!e!!e! < L;@ ;67 ; ;  ;#F#F#t#II_c(#E&(6*:":;<(#IQRZI[(# (#r,rN)collections.abcrtypingrrrrtorchrtyping_extensionsr 4torchmetrics.functional.regression.cosine_similarityr r torchmetrics.metricr torchmetrics.utilities.datar torchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr#r,r+rJs?%--%v&4@@/0m#vm#r,