Table of Contents
  • Docs >
  • Specificity At Sensitivity
Shortcuts

Specificity At Sensitivity

Module Interface

class torchmetrics.SpecificityAtSensitivity(**kwargs)[source]

Compute the highest possible specificity value given the minimum sensitivity thresholds provided.

This is done by first calculating the Receiver Operating Characteristic (ROC) curve for different thresholds and the find the specificity for a given sensitivity 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 BinarySpecificityAtSensitivity, MulticlassSpecificityAtSensitivity and MultilabelSpecificityAtSensitivity for the specific details of each argument influence and examples.

static __new__(cls, task, min_sensitivity, thresholds=None, num_classes=None, num_labels=None, ignore_index=None, validate_args=True, **kwargs)[source]

Initialize task metric.

Return type:

Metric

BinarySpecificityAtSensitivity

class torchmetrics.classification.BinarySpecificityAtSensitivity(min_sensitivity, thresholds=None, ignore_index=None, validate_args=True, **kwargs)[source]

Compute the highest possible specificity value given the minimum sensitivity thresholds provided.

This is done by first calculating the Receiver Operating Characteristic (ROC) curve for different thresholds and the find the specificity for a given sensitivity level.

Accepts the following input tensors:

  • preds (float tensor): (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 (int tensor): (N, ...). Target should be a tensor containing ground truth labels, and therefore only contain {0,1} values (except if ignore_index is specified).

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 \(\mathcal{O}(n_{samples})\) whereas setting the thresholds argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size \(\mathcal{O}(n_{thresholds})\) (constant memory).

Parameters:

  • min_sensitivity (float) – float value specifying minimum sensitivity threshold.

  • thresholds (Union[int, List[float], Tensor, None]) –

    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) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

  • kwargs (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Returns:

a tuple of 2 tensors containing:

  • specificity: an scalar tensor with the maximum specificity for the given sensitivity level

  • threshold: an scalar tensor with the corresponding threshold level

Return type:

(tuple)

Example

>>> from torchmetrics.classification import BinarySpecificityAtSensitivity
>>> from torch import tensor
>>> preds = tensor([0, 0.5, 0.4, 0.1])
>>> target = tensor([0, 1, 1, 1])
>>> metric = BinarySpecificityAtSensitivity(min_sensitivity=0.5, thresholds=None)
>>> metric(preds, target)
(tensor(1.), tensor(0.4000))
>>> metric = BinarySpecificityAtSensitivity(min_sensitivity=0.5, thresholds=5)
>>> metric(preds, target)
(tensor(1.), tensor(0.2500))

MulticlassSpecificityAtSensitivity

class torchmetrics.classification.MulticlassSpecificityAtSensitivity(num_classes, min_sensitivity, thresholds=None, ignore_index=None, validate_args=True, **kwargs)[source]

Compute the highest possible specificity value given the minimum sensitivity thresholds provided.

This is done by first calculating the Receiver Operating Characteristic (ROC) curve for different thresholds and the find the specificity for a given sensitivity level.

For multiclass the metric is calculated by iteratively treating each class as the positive class and all other classes as the negative, which is referred to as the one-vs-rest approach. One-vs-one is currently not supported by this metric.

Accepts the following input tensors:

  • preds (float tensor): (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 (int tensor): (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).

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 \(\mathcal{O}(n_{samples})\) whereas setting the thresholds argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size \(\mathcal{O}(n_{thresholds} \times n_{classes})\) (constant memory).

Parameters:

  • num_classes (int) – Integer specifying the number of classes

  • min_sensitivity (float) – float value specifying minimum sensitivity threshold.

  • thresholds (Union[int, List[float], Tensor, None]) –

    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) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

  • kwargs (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Returns:

a tuple of either 2 tensors or 2 lists containing

  • specificity: an 1d tensor of size (n_classes, ) with the maximum specificity for the given

    sensitivity level per class

  • thresholds: an 1d tensor of size (n_classes, ) with the corresponding threshold level per class

Return type:

(tuple)

Example

>>> from torchmetrics.classification import MulticlassSpecificityAtSensitivity
>>> from torch import tensor
>>> 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 = MulticlassSpecificityAtSensitivity(num_classes=5, min_sensitivity=0.5, thresholds=None)
>>> metric(preds, target)
(tensor([1., 1., 0., 0., 0.]), tensor([7.5000e-01, 7.5000e-01, 5.0000e-02, 5.0000e-02, 1.0000e+06]))
>>> metric = MulticlassSpecificityAtSensitivity(num_classes=5, min_sensitivity=0.5, thresholds=5)
>>> metric(preds, target)
(tensor([1., 1., 0., 0., 0.]), tensor([7.5000e-01, 7.5000e-01, 0.0000e+00, 0.0000e+00, 1.0000e+06]))

MultilabelSpecificityAtSensitivity

class torchmetrics.classification.MultilabelSpecificityAtSensitivity(num_labels, min_sensitivity, thresholds=None, ignore_index=None, validate_args=True, **kwargs)[source]

Compute the highest possible specificity value given the minimum sensitivity thresholds provided.

This is done by first calculating the Receiver Operating Characteristic (ROC) curve for different thresholds and the find the specificity for a given sensitivity level.

Accepts the following input tensors:

  • preds (float tensor): (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 (int tensor): (N, C, ...). Target should be a tensor containing ground truth labels, and therefore only contain {0,1} values (except if ignore_index is specified).

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 \(\mathcal{O}(n_{samples})\) whereas setting the thresholds argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size \(\mathcal{O}(n_{thresholds} \times n_{labels})\) (constant memory).

Parameters:

  • num_labels (int) – Integer specifying the number of labels

  • min_sensitivity (float) – float value specifying minimum sensitivity threshold.

  • thresholds (Union[int, List[float], Tensor, None]) –

    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) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

  • kwargs (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Returns:

a tuple of either 2 tensors or 2 lists containing

  • specificity: an 1d tensor of size (n_classes, ) with the maximum specificity for the given

    sensitivity level per class

  • thresholds: an 1d tensor of size (n_classes, ) with the corresponding threshold level per class

Return type:

(tuple)

Example

>>> from torchmetrics.classification import MultilabelSpecificityAtSensitivity
>>> from torch import tensor
>>> 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]])
>>> metric = MultilabelSpecificityAtSensitivity(num_labels=3, min_sensitivity=0.5, thresholds=None)
>>> metric(preds, target)
(tensor([1.0000, 0.5000, 1.0000]), tensor([0.7500, 0.6500, 0.3500]))
>>> metric = MultilabelSpecificityAtSensitivity(num_labels=3, min_sensitivity=0.5, thresholds=5)
>>> metric(preds, target)
(tensor([1.0000, 0.5000, 1.0000]), tensor([0.7500, 0.5000, 0.2500]))

Functional Interface

binary_specificity_at_sensitivity

torchmetrics.functional.classification.binary_specificity_at_sensitivity(preds, target, min_sensitivity, thresholds=None, ignore_index=None, validate_args=True)[source]

Compute the highest possible specificity value given the minimum sensitivity levels provided for binary tasks.

This is done by first calculating the Receiver Operating Characteristic (ROC) curve for different thresholds and the find the specificity for a given sensitivity level.

Accepts the following input tensors:

  • preds (float tensor): (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 (int tensor): (N, ...). Target should be a tensor containing ground truth labels, and therefore only contain {0,1} values (except if ignore_index is specified).

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 \(\mathcal{O}(n_{samples})\) whereas setting the thresholds argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size \(\mathcal{O}(n_{thresholds})\) (constant memory).

Parameters:

  • preds (Tensor) – Tensor with predictions

  • target (Tensor) – Tensor with true labels

  • min_sensitivity (float) – float value specifying minimum sensitivity threshold.

  • thresholds (Union[int, List[float], Tensor, None]) –

    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.

  • ignore_index (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

Returns:

a tuple of 2 tensors containing:

  • specificity: a scalar tensor with the maximum specificity for the given sensitivity level

  • threshold: a scalar tensor with the corresponding threshold level

Return type:

(tuple)

Example

>>> from torchmetrics.functional.classification import binary_specificity_at_sensitivity
>>> preds = torch.tensor([0, 0.5, 0.4, 0.1])
>>> target = torch.tensor([0, 1, 1, 1])
>>> binary_specificity_at_sensitivity(preds, target, min_sensitivity=0.5, thresholds=None)
(tensor(1.), tensor(0.4000))
>>> binary_specificity_at_sensitivity(preds, target, min_sensitivity=0.5, thresholds=5)
(tensor(1.), tensor(0.2500))

multiclass_specificity_at_sensitivity

torchmetrics.functional.classification.multiclass_specificity_at_sensitivity(preds, target, num_classes, min_sensitivity, thresholds=None, ignore_index=None, validate_args=True)[source]

Compute the highest possible specificity value given minimum sensitivity level provided for multiclass tasks.

This is done by first calculating the Receiver Operating Characteristic (ROC) curve for different thresholds and the find the specificity for a given sensitivity level.

Accepts the following input tensors:

  • preds (float tensor): (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 (int tensor): (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).

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 \(\mathcal{O}(n_{samples})\) whereas setting the thresholds argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size \(\mathcal{O}(n_{thresholds} \times n_{classes})\) (constant memory).

Parameters:

  • preds (Tensor) – Tensor with predictions

  • target (Tensor) – Tensor with true labels

  • num_classes (int) – Integer specifying the number of classes

  • min_sensitivity (float) – float value specifying minimum sensitivity threshold.

  • thresholds (Union[int, List[float], Tensor, None]) –

    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.

  • ignore_index (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

Returns:

a tuple of either 2 tensors or 2 lists containing

  • recall: an 1d tensor of size (n_classes, ) with the maximum recall for the given precision level per class

  • thresholds: an 1d tensor of size (n_classes, ) with the corresponding threshold level per class

Return type:

(tuple)

Example

>>> from torchmetrics.functional.classification import multiclass_specificity_at_sensitivity
>>> 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])
>>> multiclass_specificity_at_sensitivity(preds, target, num_classes=5, min_sensitivity=0.5, thresholds=None)
(tensor([1., 1., 0., 0., 0.]), tensor([7.5000e-01, 7.5000e-01, 5.0000e-02, 5.0000e-02, 1.0000e+06]))
>>> multiclass_specificity_at_sensitivity(preds, target, num_classes=5, min_sensitivity=0.5, thresholds=5)
(tensor([1., 1., 0., 0., 0.]), tensor([7.5000e-01, 7.5000e-01, 0.0000e+00, 0.0000e+00, 1.0000e+06]))

multilabel_specificity_at_sensitivity

torchmetrics.functional.classification.multilabel_specificity_at_sensitivity(preds, target, num_labels, min_sensitivity, thresholds=None, ignore_index=None, validate_args=True)[source]

Compute the highest possible specificity value given minimum sensitivity level provided for multilabel tasks.

This is done by first calculating the Receiver Operating Characteristic (ROC) curve for different thresholds and the find the specificity for a given sensitivity level.

Accepts the following input tensors:

  • preds (float tensor): (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 (int tensor): (N, C, ...). Target should be a tensor containing ground truth labels, and therefore only contain {0,1} values (except if ignore_index is specified).

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 \(\mathcal{O}(n_{samples})\) whereas setting the thresholds argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size \(\mathcal{O}(n_{thresholds} \times n_{labels})\) (constant memory).

Parameters:

  • preds (Tensor) – Tensor with predictions

  • target (Tensor) – Tensor with true labels

  • num_labels (int) – Integer specifying the number of labels

  • min_sensitivity (float) – float value specifying minimum sensitivity threshold.

  • thresholds (Union[int, List[float], Tensor, None]) –

    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.

  • ignore_index (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

Returns:

a tuple of either 2 tensors or 2 lists containing

  • specificity: an 1d tensor of size (n_classes, ) with the maximum recall for the given precision

    level per class

  • thresholds: an 1d tensor of size (n_classes, ) with the corresponding threshold level per class

Return type:

(tuple)

Example

>>> from torchmetrics.functional.classification import multilabel_specificity_at_sensitivity
>>> 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]])
>>> multilabel_specificity_at_sensitivity(preds, target, num_labels=3, min_sensitivity=0.5, thresholds=None)
(tensor([1.0000, 0.5000, 1.0000]), tensor([0.7500, 0.6500, 0.3500]))
>>> multilabel_specificity_at_sensitivity(preds, target, num_labels=3, min_sensitivity=0.5, thresholds=5)
(tensor([1.0000, 0.5000, 1.0000]), tensor([0.7500, 0.5000, 0.2500]))

To analyze traffic and optimize your experience, we serve cookies on this site. By clicking or navigating, you agree to allow our usage of cookies. Read PyTorch Lightning's Privacy Policy.