iRddlmZddlmZmZmZddlmZddlm Z ddl m Z ddl m Z mZmZddlmZddlmZdd lmZdd lmZdd lmZmZesgd ZGd de ZGddeZGddeZGdde Zy))Sequence)AnyOptionalUnion)Tensor)Literal)_ClassificationTaskWrapper) BinaryROC MulticlassROC MultilabelROC) _eer_compute)Metric)ClassificationTask)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE)zBinaryEER.plotzMulticlassEER.plotzMultilabelEER.plotc\eZdZdZdeffd Z ddeeeeefdee de fdZ xZ S) BinaryEERa Compute Equal Error Rate (EER) for multiclass classification task. .. math:: \text{EER} = \frac{\text{FAR} + \text{FRR}}{2}, \text{where} \min_t abs(FAR_t-FRR_t) The Equal Error Rate (EER) is the point where the False Positive Rate (FPR) and True Positive Rate (TPR) are equal, or in practise minimized. A lower EER value signifies higher system accuracy. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, ...)`` 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, ...)`` 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. As output to ``forward`` and ``compute`` the metric returns the following output: - ``b_eer`` (:class:`~torch.Tensor`): A single scalar with the eer score. Additional dimension ``...`` will be flattened into the batch dimension. The implementation both supports calculating the metric in a non-binned but accurate version and a binned version that is less accurate but more memory efficient. Setting the `thresholds` argument to `None` will activate the non-binned version that uses memory of size :math:`\mathcal{O}(n_{samples})` whereas setting the `thresholds` argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size :math:`\mathcal{O}(n_{thresholds})` (constant memory). Args: thresholds: Can be one of: - If set to `None`, will use a non-binned approach where thresholds are dynamically calculated from all the data. Most accurate but also most memory consuming approach. - If set to an `int` (larger than 1), will use that number of thresholds linearly spaced from 0 to 1 as bins for the calculation. - If set to an `list` of floats, will use the indicated thresholds in the list as bins for the calculation - If set to an 1d `tensor` of floats, will use the indicated thresholds in the tensor as bins for the 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 torch import tensor >>> from torchmetrics.classification import BinaryEER >>> preds = tensor([0, 0.5, 0.7, 0.8]) >>> target = tensor([0, 1, 1, 0]) >>> metric = BinaryEER(thresholds=None) >>> metric(preds, target) tensor(0.5000) >>> b_eer = BinaryEER(thresholds=5) >>> b_eer(preds, target) tensor(0.7500) returnc@t|\}}}t||SCompute metric.supercomputer selffprtpr_ __class__s t/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/classification/eer.pyrzBinaryEER.compute_"go' S!C%%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 >>> # Example plotting a single >>> import torch >>> from torchmetrics.classification import BinaryEER >>> metric = BinaryEER() >>> metric.update(torch.rand(20,), torch.randint(2, (20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.classification import BinaryEER >>> metric = BinaryEER() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(20,), torch.randint(2, (20,)))) >>> fig_, ax_ = metric.plot(values) _plotrr%r&s r"plotzBinaryEER.plotdPzz#r""r$NN __name__ __module__ __qualname____doc__rrrrrrrr+ __classcell__r!s@r"rr$sS8t&& _c(#E&(6*:":;<(#IQRZI[(# (#r$rc\eZdZdZdeffd Z ddeeeeefdee de fdZ xZ S) MulticlassEERa;Compute Equal Error Rate (EER) for multiclass classification task. .. math:: \text{EER} = \frac{\text{FAR} + (1 - \text{FRR})}{2}, \text{where} \min_t abs(FAR_t-FRR_t) The Equal Error Rate (EER) is the point where the False Positive Rate (FPR) and True Positive Rate (TPR) are equal, or in practise minimized. A lower EER value signifies higher system accuracy. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, C, ...)`` 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, ...)`` containing ground truth labels, and therefore only contain values in the [0, n_classes-1] range (except if `ignore_index` is specified). As output to ``forward`` and ``compute`` the metric returns the following output: - ``mc_eer`` (:class:`~torch.Tensor`): If `average=None` then a 1d tensor of shape (n_classes, ) will be returned with eer score per class. If `average="macro"|"micro"` then a single scalar will be returned. Additional dimension ``...`` will be flattened into the batch dimension. The implementation both supports calculating the metric in a non-binned but accurate version and a binned version that is less accurate but more memory efficient. Setting the `thresholds` argument to `None` will activate the non-binned version that uses memory of size :math:`\mathcal{O}(n_{samples})` whereas setting the `thresholds` argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size :math:`\mathcal{O}(n_{thresholds} \times n_{classes})` (constant memory). Args: num_classes: Integer specifying the number of classes thresholds: Can be one of: - If set to `None`, will use a non-binned approach where thresholds are dynamically calculated from all the data. Most accurate but also most memory consuming approach. - If set to an `int` (larger than 1), will use that number of thresholds linearly spaced from 0 to 1 as bins for the calculation. - If set to an `list` of floats, will use the indicated thresholds in the list as bins for the calculation - If set to an 1d `tensor` of floats, will use the indicated thresholds in the tensor as bins for the calculation. average: If aggregation of curves should be applied. By default, the curves are not aggregated and a curve for each class is returned. If `average` is set to ``"micro"``, the metric will aggregate the curves by one hot encoding the targets and flattening the predictions, considering all classes jointly as a binary problem. If `average` is set to ``"macro"``, the metric will aggregate the curves by first interpolating the curves from each class at a combined set of thresholds and then average over the classwise interpolated curves. See `averaging curve objects`_ for more info on the different averaging methods. 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. Examples: >>> from torch import tensor >>> from torchmetrics.classification import MulticlassEER >>> preds = tensor([[0.75, 0.05, 0.05, 0.05, 0.05], ... [0.05, 0.75, 0.05, 0.05, 0.05], ... [0.05, 0.05, 0.75, 0.05, 0.05], ... [0.05, 0.05, 0.05, 0.75, 0.05]]) >>> target = tensor([0, 1, 3, 2]) >>> metric = MulticlassEER(num_classes=5, average="macro", thresholds=None) >>> metric(preds, target) tensor(0.4667) >>> mc_eer = MulticlassEER(num_classes=5, average=None, thresholds=None) >>> mc_eer(preds, target) tensor([0.0000, 0.0000, 0.6667, 0.6667, 1.0000]) rc@t|\}}}t||Srrrs r"rzMulticlassEER.computer#r$r%r&c&|j||S)a5Plot 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 >>> import torch >>> from torchmetrics.classification import MulticlassEER >>> metric = MulticlassEER(num_classes=3) >>> metric.update(torch.randn(20, 3), torch.randint(3,(20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.classification import MulticlassEER >>> metric = MulticlassEER(num_classes=3) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.randn(20, 3), torch.randint(3, (20,)))) >>> fig_, ax_ = metric.plot(values) r(r*s r"r+zMulticlassEER.plotr,r$r-r.r4s@r"r6r6sTEN&& _c(#E&(6*:":;<(#IQRZI[(# (#r$r6c\eZdZdZdeffd Z ddeeeeefdee de fdZ xZ S) MultilabelEERaCompute Equal Error Rate (EER) for multiclass classification task. .. math:: \text{EER} = \frac{\text{FAR} + (1 - \text{FRR})}{2}, \text{where} \min_t abs(FAR_t-FRR_t) The Equal Error Rate (EER) is the point where the False Positive Rate (FPR) and True Positive Rate (TPR) are equal, or in practise minimized. A lower EER value signifies higher system accuracy. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, C, ...)`` 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, C, ...)`` containing ground truth labels, and therefore only contain {0,1} values (except if `ignore_index` is specified). As output to ``forward`` and ``compute`` the metric returns the following output: - ``ml_eer`` (:class:`~torch.Tensor`): A 1d tensor of shape (n_classes, ) will be returned with eer score per label. Additional dimension ``...`` will be flattened into the batch dimension. The implementation both supports calculating the metric in a non-binned but accurate version and a binned version that is less accurate but more memory efficient. Setting the `thresholds` argument to `None` will activate the non-binned version that uses memory of size :math:`\mathcal{O}(n_{samples})` whereas setting the `thresholds` argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size :math:`\mathcal{O}(n_{thresholds} \times n_{labels})` (constant memory). Args: num_labels: Integer specifying the number of labels average: Defines the reduction that is applied over labels. Should be one of the following: - ``micro``: Sum score over all labels - ``macro``: Calculate score for each label and average them - ``weighted``: calculates score for each label and computes weighted average using their support - ``"none"`` or ``None``: calculates score for each label and applies no reduction thresholds: Can be one of: - If set to `None`, will use a non-binned approach where thresholds are dynamically calculated from all the data. Most accurate but also most memory consuming approach. - If set to an `int` (larger than 1), will use that number of thresholds linearly spaced from 0 to 1 as bins for the calculation. - If set to an `list` of floats, will use the indicated thresholds in the list as bins for the calculation - If set to an 1d `tensor` of floats, will use the indicated thresholds in the tensor as bins for the 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 torch import tensor >>> from torchmetrics.classification import MultilabelEER >>> preds = tensor([[0.75, 0.05, 0.35], ... [0.45, 0.75, 0.05], ... [0.05, 0.55, 0.75], ... [0.05, 0.65, 0.05]]) >>> target = tensor([[1, 0, 1], ... [0, 0, 0], ... [0, 1, 1], ... [1, 1, 1]]) >>> ml_eer = MultilabelEER(num_labels=3, thresholds=None) >>> ml_eer(preds, target) tensor([0.5000, 0.5000, 0.1667]) rc@t|\}}}t||Srrrs r"rzMultilabelEER.computeLr#r$r%r&c&|j||S)a2Plot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single >>> import torch >>> from torchmetrics.classification import MultilabelEER >>> metric = MultilabelEER(num_labels=3) >>> metric.update(torch.rand(20,3), torch.randint(2, (20,3))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.classification import MultilabelEER >>> metric = MultilabelEER(num_labels=3) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(20,3), torch.randint(2, (20,3)))) >>> fig_, ax_ = metric.plot(values) r(r*s r"r+zMultilabelEER.plotQr,r$r-r.r4s@r"r:r:sTBH&& _c(#E&(6*:":;<(#IQRZI[(# (#r$r:ceZdZdZ ddeddeddeeee e e fdeedeed eed d eed e d e defdZde d e ddfdZddZy)EERaCompute Equal Error Rate (EER) for multiclass classification task. .. math:: \text{EER} = \frac{\text{FAR} + (1 - \text{FRR})}{2}, \text{where} \min_t abs(FAR_t-FRR_t) The Equal Error Rate (EER) is the point where the False Positive Rate (FPR) and True Positive Rate (TPR) are equal, or in practise minimized. A lower EER value signifies higher system accuracy. This module is a simple wrapper to get the task specific versions of this metric, which is done by setting the ``task`` argument to either ``'binary'``, ``'multiclass'`` or ``'multilabel'``. See the documentation of :class:`~torchmetrics.classification.BinaryEER`, :class:`~torchmetrics.classification.MulticlassEER` and :class:`~torchmetrics.classification.MultilabelEER` for the specific details of each argument influence and examples. Legacy Example: >>> from torch import tensor >>> preds = tensor([0.13, 0.26, 0.08, 0.19, 0.34]) >>> target = tensor([0, 0, 1, 1, 1]) >>> eer = EER(task="binary") >>> eer(preds, target) tensor(0.5833) >>> preds = tensor([[0.90, 0.05, 0.05], ... [0.05, 0.90, 0.05], ... [0.05, 0.05, 0.90], ... [0.85, 0.05, 0.10], ... [0.10, 0.10, 0.80]]) >>> target = tensor([0, 1, 1, 2, 2]) >>> eer = EER(task="multiclass", num_classes=3) >>> eer(preds, target) tensor([0.0000, 0.4167, 0.4167]) Nclstask)binary multiclass multilabel thresholds num_classes num_labelsaverage)macromicro ignore_index validate_argskwargsrc tj|}|j|||d|tjk(r t di|S|tj k(r6t |tstdt|dt|fd|i|S|tjk(r4t |tstdt|dt|fi|Std|d) zInitialize task metric.)rDrJrKz+`num_classes` is expected to be `int` but `z was passed.`rGz*`num_labels` is expected to be `int` but `zTask z not supported!) rfrom_strupdateBINARYr MULTICLASS isinstanceint ValueErrortyper6 MULTILABELr:) r?r@rDrErFrGrJrKrLs r"__new__z EER.__new__s"**40 Z`mno %,, ,&v& & %00 0k3/ #NtT_O`Naan!opp HgHH H %00 0j#. #MdS]N^M__l!mnn 6v6 65o677r$argscFt|jjd)zUpdate metric state.zM metric does not have a global `update` method. Use the task specific metric.NotImplementedErrorr!r/)rrYrLs r"rPz EER.updates%!~~&&''t u  r$cFt|jjd)rzN metric does not have a global `compute` method. Use the task specific metric.r[)rs r"rz EER.computes%!~~&&''u v  r$)NNNNNT)rN)r/r0r1r2rVrrrrTlistfloatrboolrrrXrPrrNr$r"r>r>|s JAE%)$(7;&*"8 %[8:;8U3U V#;<=8c] 8 SM 8 '"234 8sm888 84 C 3 4  r$r>N) collections.abcrtypingrrrtorchrtyping_extensionsr torchmetrics.classification.baser torchmetrics.classification.rocr r r *torchmetrics.functional.classification.eerr torchmetrics.metricrtorchmetrics.utilities.enumsrtorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr6r:r>rNr$r"rmsz%''%G D&;@@Uh# h#Vu#Mu#pr#Mr#jG $G r$