i ddlmZddlmZmZmZddlZddlmZddlm Z ddl m Z m Z m Z ddlmZddlmZdd lmZmZesd gZGd d eZy) )Sequence)AnyOptionalUnionN)Tensor)Literal)_generalized_dice_compute_generalized_dice_update_generalized_dice_validate_args)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzGeneralizedDiceScore.plotceZdZUdZeed<eed<dZeed<dZeed<dZ eed<d Z e ed <d Z e ed < dd e dedededdeddeddffd ZdededdfdZdefdZd deeeedfdeedefdZxZS)!GeneralizedDiceScoreaCompute `Generalized Dice Score`_. The metric can be used to evaluate the performance of image segmentation models. The Generalized Dice Score is defined as: .. math:: GDS = \frac{2 \\sum_{i=1}^{N} w_i \\sum_{j} t_{ij} p_{ij}}{ \\sum_{i=1}^{N} w_i \\sum_{j} t_{ij} + \\sum_{i=1}^{N} w_i \\sum_{j} p_{ij}} where :math:`N` is the number of classes, :math:`t_{ij}` is the target tensor, :math:`p_{ij}` is the prediction tensor, and :math:`w_i` is the weight for class :math:`i`. The weight can be computed in three different ways: - `square`: :math:`w_i = 1 / (\\sum_{j} t_{ij})^2` - `simple`: :math:`w_i = 1 / \\sum_{j} t_{ij}` - `linear`: :math:`w_i = 1` Note that the generalized dice loss can be computed as one minus the generalized dice score. 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 to ``forward`` and ``compute`` the metric returns the following output: - ``gds`` (:class:`~torch.Tensor`): The generalized dice score. If ``per_class`` is set to ``True``, the output will be a tensor of shape ``(C,)`` with the generalized dice score for each class. If ``per_class`` is set to ``False``, the output will be a scalar tensor. Args: num_classes: The number of classes in the segmentation problem. include_background: Whether to include the background class in the computation per_class: Whether to compute the metric for each class separately. weight_type: The type of weight to apply to each class. Can be one of ``"square"``, ``"simple"``, or ``"linear"``. input_format: What kind of input the function receives. Choose between ``"one-hot"`` for one-hot encoded tensors, ``"index"`` for index tensors or ``"mixed"`` for one one-hot encoded and one index tensor kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If ``num_classes`` is not a positive integer ValueError: If ``include_background`` is not a boolean ValueError: If ``per_class`` is not a boolean ValueError: If ``weight_type`` is not one of ``"square"``, ``"simple"``, or ``"linear"`` ValueError: If ``input_format`` is not one of ``"one-hot"``, ``"index"`` or ``"mixed"`` Example: >>> from torch import randint >>> from torchmetrics.segmentation import GeneralizedDiceScore >>> gds = GeneralizedDiceScore(num_classes=3) >>> preds = randint(0, 2, (10, 3, 128, 128)) >>> target = randint(0, 2, (10, 3, 128, 128)) >>> gds(preds, target) tensor(0.4992) >>> gds = GeneralizedDiceScore(num_classes=3, per_class=True) >>> gds(preds, target) tensor([0.5001, 0.4993, 0.4982]) >>> gds = GeneralizedDiceScore(num_classes=3, per_class=True, include_background=False) >>> gds(preds, target) tensor([0.4993, 0.4982]) scoresamplesFfull_state_updateis_differentiableThigher_is_bettergplot_lower_boundg?plot_upper_bound num_classesinclude_background per_class weight_type)squaresimplelinear input_format)one-hotindexmixedkwargsreturnNc >t|di|t|||||||_||_||_||_||_|s|dz n|}|jdtj|r|ndd|jdtjddy)Nrsum)defaultdist_reduce_fxr) super__init__r rrrrr add_statetorchzeros)selfrrrrr r$ __class__s /Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/segmentation/generalized_dice.pyr-zGeneralizedDiceScore.__init__vs "6"' 5GT_amn&"4"&(-?kAo[  w 9KRS(Tejk y%++a.Opredstargetc2t|||j|j|j|j\}}|xj t |||jjdz c_|xj|jdz c_ y)zUpdate the state with new data.r)dimN) r rrrr rr rr(rshape)r1r5r6 numerator denominators r3updatezGeneralizedDiceScore.updatesz!9 64++T-D-DdFVFVX\XiXi"  ; / ;W[[`a[bb   A& r4c4|j|jz S)z)Compute the final generalized dice score.)rr)r1s r3computezGeneralizedDiceScore.computeszzDLL((r4valaxc&|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.segmentation import GeneralizedDiceScore >>> metric = GeneralizedDiceScore(num_classes=3) >>> metric.update(torch.randint(0, 2, (10, 3, 128, 128)), torch.randint(0, 2, (10, 3, 128, 128))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.segmentation import GeneralizedDiceScore >>> metric = GeneralizedDiceScore(num_classes=3) >>> values = [ ] >>> for _ in range(10): ... values.append( ... metric(torch.randint(0, 2, (10, 3, 128, 128)), torch.randint(0, 2, (10, 3, 128, 128))) ... ) >>> fig_, ax_ = metric.plot(values) )_plot)r1r?r@s r3plotzGeneralizedDiceScore.plotsPzz#r""r4)TFrr!)NN)__name__ __module__ __qualname____doc__r__annotations__rboolrrrfloatrintrrr-r<r>rrrrrrC __classcell__)r2s@r3rr"sIV M O#t##t#!d!!e!!e! $(=E=F PP!P P 9: P 9: PP P*'F'F't'))(#fhv&6<=(#(S[J\(#hv(#r4r)collections.abcrtypingrrrr/rtyping_extensionsr5torchmetrics.functional.segmentation.generalized_dicer r r torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotrr__doctest_skip__rr+r4r3rUsH%'' % '@@34]#6]#r4