o yiLF@sddlmZmZmZmZmZddlZddlmZddlm Z ddl m Z m Z m Z ddlmZmZmZmZmZmZddlmZddlmZGd d d e ZGd d d e ZGd dde ZGdddZdS))AnyListOptionalTupleUnionN)Tensor)Literal)BinaryPrecisionRecallCurveMulticlassPrecisionRecallCurveMultilabelPrecisionRecallCurve)0_binary_recall_at_fixed_precision_arg_validation)_binary_recall_at_fixed_precision_compute1_multiclass_recall_at_fixed_precision_arg_compute4_multiclass_recall_at_fixed_precision_arg_validation1_multilabel_recall_at_fixed_precision_arg_compute4_multilabel_recall_at_fixed_precision_arg_validation)Metric) dim_zero_catc seZdZUdZdZeed<dZeeed<dZ eed<   dde d ee e e e efd ee d ed ed df fdd Zd eeeffddZZS)BinaryRecallAtFixedPrecisiona Computes the highest possible recall value given the minimum precision thresholds provided. This is done by first calculating the precision-recall curve for different thresholds and the find the recall for a given precision level. 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. .. note:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns the following output: - ``recall`` (:class:`~torch.Tensor`): A scalar tensor with the maximum recall for the given precision level - ``threshold`` (:class:`~torch.Tensor`): A scalar tensor with the corresponding threshold level .. note:: 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: min_precision: float value specifying minimum precision threshold. 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 torchmetrics.classification import BinaryRecallAtFixedPrecision >>> preds = torch.tensor([0, 0.5, 0.7, 0.8]) >>> target = torch.tensor([0, 1, 1, 0]) >>> metric = BinaryRecallAtFixedPrecision(min_precision=0.5, thresholds=None) >>> metric(preds, target) (tensor(1.), tensor(0.5000)) >>> metric = BinaryRecallAtFixedPrecision(min_precision=0.5, thresholds=5) >>> metric(preds, target) (tensor(1.), tensor(0.5000)) Fis_differentiableNhigher_is_betterfull_state_updateT min_precision thresholds ignore_index validate_argskwargsreturnc s:tj||fddi||rt|||||_||_dS)NrF)super__init__r rr)selfrrrrr __class__i/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/classification/recall_at_fixed_precision.pyrbs   z%BinaryRecallAtFixedPrecision.__init__cCs6|jdurt|jt|jg}n|j}t||j|jSN)rrpredstargetconfmatr rr stater#r#r$computeps z$BinaryRecallAtFixedPrecision.computeNNT)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrintrrrrrr+ __classcell__r#r#r!r$r%s,  8 rceZdZUdZdZeed<dZeeed<dZ eed<   dde d e d ee e e e efd ee d ed eddffdd ZdeeeffddZZS) MulticlassRecallAtFixedPrecisiona:Computes the highest possible recall value given the minimum precision thresholds provided. This is done by first calculating the precision-recall curve for different thresholds and the find the recall for a given precision level. 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). .. note:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns a tuple of either 2 tensors or 2 lists containing: - ``recall`` (:class:`~torch.Tensor`): A 1d tensor of size ``(n_classes, )`` with the maximum recall for the given precision level per class - ``threshold`` (:class:`~torch.Tensor`): A 1d tensor of size ``(n_classes, )`` with the corresponding threshold level per class .. note:: 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 specifing the number of classes min_precision: float value specifying minimum precision threshold. 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 torchmetrics.classification import MulticlassRecallAtFixedPrecision >>> preds = torch.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 = torch.tensor([0, 1, 3, 2]) >>> metric = MulticlassRecallAtFixedPrecision(num_classes=5, min_precision=0.5, thresholds=None) >>> metric(preds, target) (tensor([1., 1., 0., 0., 0.]), tensor([7.5000e-01, 7.5000e-01, 1.0000e+06, 1.0000e+06, 1.0000e+06])) >>> mcrafp = MulticlassRecallAtFixedPrecision(num_classes=5, min_precision=0.5, thresholds=5) >>> mcrafp(preds, target) (tensor([1., 1., 0., 0., 0.]), tensor([7.5000e-01, 7.5000e-01, 1.0000e+06, 1.0000e+06, 1.0000e+06])) FrNrrT num_classesrrrrrrc >tjd|||dd||rt||||||_||_dS)NF)r8rrrr#)rrrrr)r r8rrrrrr!r#r$r  z)MulticlassRecallAtFixedPrecision.__init__cCs:|jdurt|jt|jg}n|j}t||j|j|jSr%)rrr&r'r(rr8rr)r#r#r$r+s z(MulticlassRecallAtFixedPrecision.computer,r-r.r/r0rr1r2rrrr4r3rrrrrrr+r5r#r#r!r$r7xs0  > r7cr6) MultilabelRecallAtFixedPrecisionaNComputes the highest possible recall value given the minimum precision thresholds provided. This is done by first calculating the precision-recall curve for different thresholds and the find the recall for a given precision level. 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 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. .. note:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns a tuple of either 2 tensors or 2 lists containing: - ``recall`` (:class:`~torch.Tensor`): A 1d tensor of size ``(n_classes, )`` with the maximum recall for the given precision level per class - ``threshold`` (:class:`~torch.Tensor`): A 1d tensor of size ``(n_classes, )`` with the corresponding threshold level per class .. note:: 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 specifing the number of labels min_precision: float value specifying minimum precision threshold. 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 torchmetrics.classification import MultilabelRecallAtFixedPrecision >>> preds = torch.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 = torch.tensor([[1, 0, 1], ... [0, 0, 0], ... [0, 1, 1], ... [1, 1, 1]]) >>> metric = MultilabelRecallAtFixedPrecision(num_labels=3, min_precision=0.5, thresholds=None) >>> metric(preds, target) (tensor([1., 1., 1.]), tensor([0.0500, 0.5500, 0.0500])) >>> mlrafp = MultilabelRecallAtFixedPrecision(num_labels=3, min_precision=0.5, thresholds=5) >>> mlrafp(preds, target) (tensor([1., 1., 1.]), tensor([0.0000, 0.5000, 0.0000])) FrNrrT num_labelsrrrrrrc r9)NF)r=rrrr#)rrrrr)r r=rrrrrr!r#r$rr:z)MultilabelRecallAtFixedPrecision.__init__cCs>|jdurt|jt|jg}n|j}t||j|j|j|jSr%) rrr&r'r(rr=rrr)r#r#r$r+-s z(MultilabelRecallAtFixedPrecision.computer,r;r#r#r!r$r<s0  A r<c@sleZdZdZ     ddeddedeeee ee fdeed eed eed e d e d e fddZdS)RecallAtFixedPrecisionaComputes the highest possible recall value given the minimum precision thresholds provided. This is done by first calculating the precision-recall curve for different thresholds and the find the recall for a given precision level. This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the ``task`` argument to either ``'binary'``, ``'multiclass'`` or ``multilabel``. See the documentation of :mod:`BinaryRecallAtFixedPrecision`, :func:`MulticlassRecallAtFixedPrecision` and :func:`MultilabelRecallAtFixedPrecision` for the specific details of each argument influence and examples. NTtask)binary multiclass multilabelrrr8r=rrrrc Ks|dkrt||||fi|S|dkr&t|tsJt|||||fi|S|dkr=t|ts1Jt|||||fi|Std|)Nr@rArBz[Expected argument `task` to either be `'binary'`, `'multiclass'` or `'multilabel'` but got )r isinstancer4r7r< ValueError) clsr?rrr8r=rrrr#r#r$__new__Bs&   zRecallAtFixedPrecision.__new__)NNNNT)r-r.r/r0rr3rrr4rrr1rrrFr#r#r#r$r>7s4  r>)typingrrrrrtorchrtyping_extensionsr2torchmetrics.classification.precision_recall_curver r r @torchmetrics.functional.classification.recall_at_fixed_precisionr r rrrrtorchmetrics.metricrtorchmetrics.utilities.datarrr7r<r>r#r#r#r$s      S^a