ifddlmZddlmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z ddlmZdd lmZmZesd gZGd d e Zy) )Sequence)AnyOptionalUnionN)Tensor)Literal)Metric)procrustes_disparity)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzProcrustesDisparity.plotceZdZUdZeed<eed<dZeed<dZeed<dZ eed<dZ e ed <d Z e ed <dd e d deddffd ZdejdejddfdZdejfdZddeeeedfdeedefdZxZS)ProcrustesDisparityakCompute the `Procrustes Disparity`_. The Procrustes Disparity is defined as the sum of the squared differences between two datasets after applying a Procrustes transformation. The Procrustes Disparity is useful to compare two datasets that are similar but not aligned. The metric works similar to ``scipy.spatial.procrustes`` but for batches of data points. The disparity is aggregated over the batch, thus to get the individual disparities please use the functional version of this metric: ``torchmetrics.functional.shape.procrustes.procrustes_disparity``. As input to ``forward`` and ``update`` the metric accepts the following input: - ``point_cloud1`` (torch.Tensor): A tensor of shape ``(N, M, D)`` with ``N`` being the batch size, ``M`` the number of data points and ``D`` the dimensionality of the data points. - ``point_cloud2`` (torch.Tensor): A tensor of shape ``(N, M, D)`` with ``N`` being the batch size, ``M`` the number of data points and ``D`` the dimensionality of the data points. As output to ``forward`` and ``compute`` the metric returns the following output: - ``gds`` (:class:`~torch.Tensor`): A scalar tensor with the Procrustes Disparity. Args: reduction: Determines whether to return the mean disparity or the sum of the disparities. Can be one of ``"mean"`` or ``"sum"``. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If ``average`` is not one of ``"mean"`` or ``"sum"``. Example: >>> from torch import randn >>> from torchmetrics.shape import ProcrustesDisparity >>> metric = ProcrustesDisparity() >>> point_cloud1 = randn(10, 50, 2) >>> point_cloud2 = randn(10, 50, 2) >>> metric(point_cloud1, point_cloud2) tensor(0.9770) disparitytotalFfull_state_updateis_differentiablehigher_is_betterplot_lower_boundg?plot_upper_bound reductionmeansumkwargsreturnNc t|d i||dvrtd|||_|j dt j dd|j dt j ddy) Nrz9Argument `reduction` must be one of ['mean', 'sum'], got rrr)defaultdist_reduce_fxrr)super__init__ ValueErrorr add_statetorchtensor)selfrr __class__s r/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/shape/procrustes.pyr#zProcrustesDisparity.__init__Psl "6" O +XYbXcde e" {ELL,=eT w QN point_cloud1 point_cloud2ct||}|xj|jz c_|xj|j z c_y)z8Update the Procrustes Disparity with the given datasets.N)r rrrnumel)r(r,r-rs r*updatezProcrustesDisparity.updateXs70|L  )--/) ioo'' r+cj|jdk(r|j|jz S|jS)z"Computes the Procrustes Disparity.r)rrr)r(s r*computezProcrustesDisparity.compute^s+ >>V #>>DJJ. .~~r+valaxc&|j||S)a.Plot 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.shape import ProcrustesDisparity >>> metric = ProcrustesDisparity() >>> metric.update(torch.randn(10, 50, 2), torch.randn(10, 50, 2)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.shape import ProcrustesDisparity >>> metric = ProcrustesDisparity() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.randn(10, 50, 2), torch.randn(10, 50, 2))) >>> fig_, ax_ = metric.plot(values) )_plot)r(r3r4s r*plotzProcrustesDisparity.plotdsLzz#r""r+)r)NN)__name__ __module__ __qualname____doc__r__annotations__rboolrrrfloatrrrr#r&r0r2rrrr r r7 __classcell__)r)s@r*rrs'R M#t##t#"d"!e!!e!O'-"8OSOUYO(5<<(u||(PT(  &#fhv&6<=&#(S[J\&#hv&#r+r)collections.abcrtypingrrrr&rtyping_extensionsr torchmetricsr (torchmetrics.functional.shape.procrustesr torchmetrics.utilities.importsr torchmetrics.utilities.plotr r __doctest_skip__rr!r+r*rHs?%'' %I@@23l#&l#r+