o .wi@sddlmZddlmZmZmZmZddlZddlmZddl m Z m Z ddl m Z ddlmZddlmZmZes=d gZGd d d e ZdS) )Sequence)AnyLiteralOptionalUnionN)Tensor)!_hausdorff_distance_validate_argshausdorff_distance)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEHausdorffDistance.plotcseZdZUdZdZeed<dZeed<dZeed<dZ e ed<e ed <e ed <   d$de dede ddeee ee fdede ddedd ffdd Zde de dd fddZde fddZ d%d eee ee fd!eedefd"d#ZZS)&HausdorffDistancea Compute the `Hausdorff Distance`_ between two subsets of a metric space for semantic segmentation. .. math:: d_{\Pi}(X,Y) = \max{/sup_{x\in X} {d(x,Y)}, /sup_{y\in Y} {d(X,y)}} where :math:`\X, \Y` are two subsets of a metric space with distance metric :math:`d`. The Hausdorff distance is the maximum distance from a point in one set to the closest point in the other set. The Hausdorff distance is a measure of the degree of mismatch between two sets. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): An one-hot boolean tensor of shape ``(N, C, ...)`` with ``N`` being the number of samples and ``C`` the number of classes. Alternatively, an integer tensor of shape ``(N, ...)`` can be provided, where the integer values correspond to the class index. The input type can be controlled with the ``input_format`` argument. - ``target`` (:class:`~torch.Tensor`): An one-hot boolean tensor of shape ``(N, C, ...)`` with ``N`` being the number of samples and ``C`` the number of classes. Alternatively, an integer tensor of shape ``(N, ...)`` can be provided, where the integer values correspond to the class index. The input type can be controlled with the ``input_format`` argument. As output of ``forward`` and ``compute`` the metric returns the following output: - ``hausdorff_distance`` (:class:`~torch.Tensor`): A scalar float tensor with the Hausdorff distance averaged over classes and samples Args: num_classes: number of classes include_background: whether to include background class in calculation distance_metric: distance metric to calculate surface distance. Choose one of `"euclidean"`, `"chessboard"` or `"taxicab"` spacing: spacing between pixels along each spatial dimension. If not provided the spacing is assumed to be 1 directed: whether to calculate directed or undirected Hausdorff distance input_format: What kind of input the function receives. Choose between ``"one-hot"`` for one-hot encoded tensors or ``"index"`` for index tensors kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import randint >>> from torchmetrics.segmentation import HausdorffDistance >>> preds = randint(0, 2, (4, 5, 16, 16)) # 4 samples, 5 classes, 16x16 prediction >>> target = randint(0, 2, (4, 5, 16, 16)) # 4 samples, 5 classes, 16x16 target >>> hausdorff_distance = HausdorffDistance(distance_metric="euclidean", num_classes=5) >>> hausdorff_distance(preds, target) tensor(1.9567) Tis_differentiableFhigher_is_betterfull_state_updateplot_lower_boundscoretotal euclideanNone-hot num_classesinclude_backgrounddistance_metric)r chessboardtaxicabspacingdirected input_format)rindexkwargsreturnc sxtjdi|t||||||||_||_||_||_||_||_|j dt ddd|j dt ddddS)Nrrsum)defaultdist_reduce_fxrr) super__init__rrrrrrr add_statetorchtensor)selfrrrrrr r" __class__r'i/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/segmentation/hausdorff_distance.pyr)Ws  zHausdorffDistance.__init__predstargetc CsLt|||j|j|j|j|j|jd}|j|7_|j | 7_ dS)z*Update state with predictions and targets.)rrrrr N) r rrrrrr rr$rnumel)r-r1r2rr'r'r0updatens zHausdorffDistance.updatecCs |j|jS)z-Compute final Hausdorff distance over states.)rr)r-r'r'r0compute}s zHausdorffDistance.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 >>> from torch import randint >>> from torchmetrics.segmentation import HausdorffDistance >>> preds = randint(0, 2, (4, 5, 16, 16)) # 4 samples, 5 classes, 16x16 prediction >>> target = randint(0, 2, (4, 5, 16, 16)) # 4 samples, 5 classes, 16x16 target >>> metric = HausdorffDistance(num_classes=5) >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() )_plot)r-r6r7r'r'r0plots r)FrNFr)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrintrrrlistrr)r4r5rr r r9 __classcell__r'r'r.r0rsP  /    r)collections.abcrtypingrrrrr+r7torchmetrics.functional.segmentation.hausdorff_distancerr torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotr r __doctest_skip__rr'r'r'r0s