i=ddlmZddlmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z mZmZmZmZmZmZmZmZddlmZdd lmZdd lmZdd lmZmZesd d gZGddeZ GddeZ!Gdde Z"y))Sequence)AnyOptionalUnionN)Tensor)Literal)_ClassificationTaskWrapper) _binary_confusion_matrix_format!_binary_hinge_loss_arg_validation$_binary_hinge_loss_tensor_validation_binary_hinge_loss_update_hinge_loss_compute#_multiclass_confusion_matrix_format%_multiclass_hinge_loss_arg_validation(_multiclass_hinge_loss_tensor_validation_multiclass_hinge_loss_update)Metric)ClassificationTaskNoMultilabel)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzBinaryHingeLoss.plotzMulticlassHingeLoss.plotc eZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e ed <e ed < ddede edededd f fd Zde de dd fdZde fdZ dde ee ee fde edefdZxZS)BinaryHingeLossa'Compute the mean `Hinge loss`_ typically used for Support Vector Machines (SVMs) for binary tasks. .. math:: \text{Hinge loss} = \max(0, 1 - y \times \hat{y}) Where :math:`y \in {-1, 1}` is the target, and :math:`\hat{y} \in \mathbb{R}` is the prediction. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, ...)``. Preds should be a tensor containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``. Target should be a tensor containing ground truth labels, and therefore only contain {0,1} values (except if `ignore_index` is specified). The value 1 always encodes the positive class. .. tip:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns the following output: - ``bhl`` (:class:`~torch.Tensor`): A tensor containing the hinge loss. Args: squared: If True, this will compute the squared hinge loss. Otherwise, computes the regular hinge loss. ignore_index: Specifies a target value that is ignored and does not contribute to the metric calculation validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torchmetrics.classification import BinaryHingeLoss >>> preds = torch.tensor([0.25, 0.25, 0.55, 0.75, 0.75]) >>> target = torch.tensor([0, 0, 1, 1, 1]) >>> bhl = BinaryHingeLoss() >>> bhl(preds, target) tensor(0.6900) >>> bhl = BinaryHingeLoss(squared=True) >>> bhl(preds, target) tensor(0.6905) Tis_differentiableFhigher_is_betterfull_state_updateplot_lower_bound?plot_upper_boundmeasurestotalNsquared ignore_index validate_argskwargsreturnc t|di||r t||||_||_||_|j dtjdd|j dtjddy)Nr!rsumdefaultdist_reduce_fxr"r) super__init__r r%r#r$ add_statetorchtensor)selfr#r$r%r& __class__s v/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/classification/hinge.pyr/zBinaryHingeLoss.__init__asn "6"  -g| D* ( z5<<+>> # Example plotting a single value >>> from torch import rand, randint >>> from torchmetrics.classification import BinaryHingeLoss >>> metric = BinaryHingeLoss() >>> metric.update(rand(10), randint(2,(10,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torch import rand, randint >>> from torchmetrics.classification import BinaryHingeLoss >>> metric = BinaryHingeLoss() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(rand(10), randint(2,(10,)))) >>> fig_, ax_ = metric.plot(values) _plotr3rErFs r5plotzBinaryHingeLoss.plotPzz#r""r6)FNTNN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatr rrintrr/r>rCrrrrrK __classcell__r4s@r5rr*s+Z#t""d"#t#!e!!e! M&*" OOsmO O  O  O" F F t >> _c(#E&(6*:":;<(#IQRZI[(# (#r6rceZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <d Z e ed <eed <eed< d dedededdeedededdffd ZdededdfdZdefdZ d!deeeeefdeedefdZxZS)"MulticlassHingeLossa Compute the mean `Hinge loss`_ typically used for Support Vector Machines (SVMs) for multiclass tasks. The metric can be computed in two ways. Either, the definition by Crammer and Singer is used: .. math:: \text{Hinge loss} = \max\left(0, 1 - \hat{y}_y + \max_{i \ne y} (\hat{y}_i)\right) Where :math:`y \in {0, ..., \mathrm{C}}` is the target class (where :math:`\mathrm{C}` is the number of classes), and :math:`\hat{y} \in \mathbb{R}^\mathrm{C}` is the predicted output per class. Alternatively, the metric can also be computed in one-vs-all approach, where each class is valued against all other classes in a binary fashion. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, C, ...)``. Preds should be a tensor containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider the input to be logits and will auto apply softmax per sample. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``. Target should be a tensor containing ground truth labels, and therefore only contain values in the [0, n_classes-1] range (except if `ignore_index` is specified). .. tip:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns the following output: - ``mchl`` (:class:`~torch.Tensor`): A tensor containing the multi-class hinge loss. Args: num_classes: Integer specifying the number of classes squared: If True, this will compute the squared hinge loss. Otherwise, computes the regular hinge loss. multiclass_mode: Determines how to compute the metric ignore_index: Specifies a target value that is ignored and does not contribute to the metric calculation validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torchmetrics.classification import MulticlassHingeLoss >>> preds = torch.tensor([[0.25, 0.20, 0.55], ... [0.55, 0.05, 0.40], ... [0.10, 0.30, 0.60], ... [0.90, 0.05, 0.05]]) >>> target = torch.tensor([0, 1, 2, 0]) >>> mchl = MulticlassHingeLoss(num_classes=3) >>> mchl(preds, target) tensor(0.9125) >>> mchl = MulticlassHingeLoss(num_classes=3, squared=True) >>> mchl(preds, target) tensor(1.1131) >>> mchl = MulticlassHingeLoss(num_classes=3, multiclass_mode='one-vs-all') >>> mchl(preds, target) tensor([0.8750, 1.1250, 1.1000]) TrFrrrrrr Classplot_legend_namer!r"N num_classesr#multiclass_modecrammer-singerz one-vs-allr$r%r&r'c nt|di||rt||||||_||_||_||_||_|jd|j dk(rtjdntj|d|jdtjddy) Nr!r_rr)r*r"rr-) r.r/rr%r\r#r]r$r0r1r2zeros)r3r\r#r]r$r%r&r4s r5r/zMulticlassHingeLoss.__init__s "6"  1+wYe f*& .(  ##'77LL%!   w QNr6r7r8c6|jr"t|||j|jt |||jd\}}t |||j |j\}}|xj|z c_|xj|z c_ y)r:F)r<N) r%rr\r$rrr#r]r!r"r=s r5r>zMulticlassHingeLoss.updates|    4UFDDTDTVZVgVg h;E64K\K\puv v7vt||UYUiUij% !  e r6cBt|j|jSr@rArBs r5rCzMulticlassHingeLoss.computerDr6rErFc&|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 object and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value per class >>> from torch import randint, randn >>> from torchmetrics.classification import MulticlassHingeLoss >>> metric = MulticlassHingeLoss(num_classes=3) >>> metric.update(randn(20, 3), randint(3, (20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting a multiple values per class >>> from torch import randint, randn >>> from torchmetrics.classification import MulticlassHingeLoss >>> metric = MulticlassHingeLoss(num_classes=3) >>> values = [] >>> for _ in range(20): ... values.append(metric(randn(20, 3), randint(3, (20,)))) >>> fig_, ax_ = metric.plot(values) rHrJs r5rKzMulticlassHingeLoss.plotrLr6)Fr_NTrM)rNrOrPrQrrRrSrrrrTr r[strrrUrrrr/r>rCrrrrrKrVrWs@r5rYrYs%8t#t""d"#t#!e!!e!#c# M CS&*" OOO!!?@ O sm O  OO O:FFt>> _c(#E&(6*:":;<(#IQRZI[(# (#r6rYcleZdZdZ ddeddeddeededeed d eed ed e d e fdZ y) HingeLossaCompute the mean `Hinge loss`_ typically used for Support Vector Machines (SVMs). This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the ``task`` argument to either ``'binary'`` or ``'multiclass'``. See the documentation of :class:`~torchmetrics.classification.BinaryHingeLoss` and :class:`~torchmetrics.classification.MulticlassHingeLoss` for the specific details of each argument influence and examples. Legacy Example: >>> from torch import tensor >>> target = tensor([0, 1, 1]) >>> preds = tensor([0.5, 0.7, 0.1]) >>> hinge = HingeLoss(task="binary") >>> hinge(preds, target) tensor(0.9000) >>> target = tensor([0, 1, 2]) >>> preds = tensor([[-1.0, 0.9, 0.2], [0.5, -1.1, 0.8], [2.2, -0.5, 0.3]]) >>> hinge = HingeLoss(task="multiclass", num_classes=3) >>> hinge(preds, target) tensor(1.5551) >>> target = tensor([0, 1, 2]) >>> preds = tensor([[-1.0, 0.9, 0.2], [0.5, -1.1, 0.8], [2.2, -0.5, 0.3]]) >>> hinge = HingeLoss(task="multiclass", num_classes=3, multiclass_mode="one-vs-all") >>> hinge(preds, target) tensor([1.3743, 1.1945, 1.2359]) Nclstask)binary multiclassr\r#r]r^r$r%r&r'c htj|}|j||d|tjk(r t |fi|S|tj k(rIt |tstdt|d|dvrtd|dt|||fi|Std|d) zInitialize task metric.)r$r%z+`num_classes` is expected to be `int` but `z was passed.`r^zQ`multiclass_mode` is expected to be one of 'crammer-singer' or 'one-vs-all' but `z ` was passed.zUnsupported task ``) rfrom_strr>BINARYr MULTICLASS isinstancerU ValueErrortyperY)rhrir\r#r]r$r%r&s r5__new__zHingeLoss.__new__ds.66t< |mTU 188 8"75f5 5 1<< <k3/ #NtT_O`Naan!opp&FF '( 7'{G_WPVW W-dV1566r6)NFr_NT) rNrOrPrQrsrrrUrRrrrtr-r6r5rgrgFs@&*M]&*"7 + 7,-7c]7 7 "'*H"IJ 7 sm 777 7r6rg)#collections.abcrtypingrrrr1rtyping_extensionsr torchmetrics.classification.baser ,torchmetrics.functional.classification.hinger r r r rrrrrtorchmetrics.metricrtorchmetrics.utilities.enumsrtorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rrYrgr-r6r5rss%'' %G   'G@@.0JK#f#DW#&W#t67*67r6