Calibration Error¶
Module Interface¶
- class torchmetrics.CalibrationError(task: Optional[Literal['binary', 'multiclass']] = None, n_bins: int = 15, norm: Literal['l1', 'l2', 'max'] = 'l1', num_classes: Optional[int] = None, ignore_index: Optional[int] = None, validate_args: bool = True, **kwargs: Any)[source]
Computes the Top-label Calibration Error. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution.
Three different norms are implemented, each corresponding to variations on the calibration error metric.
Where is the top-1 prediction accuracy in bin , is the average confidence of predictions in bin , and is the fraction of data points in bin . Bins are constructed in an uniform way in the [0,1] range.
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 ofBinaryCalibrationError
andMulticlassCalibrationError
for the specific details of each argument influence and examples.
BinaryCalibrationError¶
- class torchmetrics.classification.BinaryCalibrationError(n_bins=15, norm='l1', ignore_index=None, validate_args=True, **kwargs)[source]
Computes the Top-label Calibration Error for binary tasks. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution.
Three different norms are implemented, each corresponding to variations on the calibration error metric.
Where is the top-1 prediction accuracy in bin , is the average confidence of predictions in bin , and is the fraction of data points in bin . Bins are constructed in an uniform way in the [0,1] range.
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.- Parameters
n_bins¶ (
int
) – Number of bins to use when computing the metric.norm¶ (
Literal
[‘l1’, ‘l2’, ‘max’]) – Norm used to compare empirical and expected probability bins.ignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ (
Any
) – Additional keyword arguments, see Advanced metric settings for more info.
Example
>>> from torchmetrics.classification import BinaryCalibrationError >>> preds = torch.tensor([0.25, 0.25, 0.55, 0.75, 0.75]) >>> target = torch.tensor([0, 0, 1, 1, 1]) >>> metric = BinaryCalibrationError(n_bins=2, norm='l1') >>> metric(preds, target) tensor(0.2900) >>> metric = BinaryCalibrationError(n_bins=2, norm='l2') >>> metric(preds, target) tensor(0.2918) >>> metric = BinaryCalibrationError(n_bins=2, norm='max') >>> metric(preds, target) tensor(0.3167)
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- compute()[source]
Override this method to compute the final metric value from state variables synchronized across the distributed backend.
- Return type
MulticlassCalibrationError¶
- class torchmetrics.classification.MulticlassCalibrationError(num_classes, n_bins=15, norm='l1', ignore_index=None, validate_args=True, **kwargs)[source]
Computes the Top-label Calibration Error for multiclass tasks. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution.
Three different norms are implemented, each corresponding to variations on the calibration error metric.
Where is the top-1 prediction accuracy in bin , is the average confidence of predictions in bin , and is the fraction of data points in bin . Bins are constructed in an uniform way in the [0,1] range.
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.- Parameters
num_classes¶ (
int
) – Integer specifing the number of classesn_bins¶ (
int
) – Number of bins to use when computing the metric.norm¶ (
Literal
[‘l1’, ‘l2’, ‘max’]) – Norm used to compare empirical and expected probability bins.ignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ (
Any
) – Additional keyword arguments, see Advanced metric settings for more info.
Example
>>> from torchmetrics.classification import MulticlassCalibrationError >>> 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]) >>> metric = MulticlassCalibrationError(num_classes=3, n_bins=3, norm='l1') >>> metric(preds, target) tensor(0.2000) >>> metric = MulticlassCalibrationError(num_classes=3, n_bins=3, norm='l2') >>> metric(preds, target) tensor(0.2082) >>> metric = MulticlassCalibrationError(num_classes=3, n_bins=3, norm='max') >>> metric(preds, target) tensor(0.2333)
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- compute()[source]
Override this method to compute the final metric value from state variables synchronized across the distributed backend.
- Return type
Functional Interface¶
- torchmetrics.functional.calibration_error(preds, target, task=None, n_bins=15, norm='l1', num_classes=None, ignore_index=None, validate_args=True)[source]
Computes the Top-label Calibration Error. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution.
Three different norms are implemented, each corresponding to variations on the calibration error metric.
Where is the top-1 prediction accuracy in bin , is the average confidence of predictions in bin , and is the fraction of data points in bin . Bins are constructed in an uniform way in the [0,1] range.
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 ofbinary_calibration_error()
andmulticlass_calibration_error()
for the specific details of each argument influence and examples.- Return type
binary_calibration_error¶
- torchmetrics.functional.classification.binary_calibration_error(preds, target, n_bins=15, norm='l1', ignore_index=None, validate_args=True)[source]
Computes the Top-label Calibration Error for binary tasks. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution.
Three different norms are implemented, each corresponding to variations on the calibration error metric.
Where is the top-1 prediction accuracy in bin , is the average confidence of predictions in bin , and is the fraction of data points in bin . Bins are constructed in an uniform way in the [0,1] range.
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.- Parameters
n_bins¶ (
int
) – Number of bins to use when computing the metric.norm¶ (
Literal
[‘l1’, ‘l2’, ‘max’]) – Norm used to compare empirical and expected probability bins.ignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.
Example
>>> from torchmetrics.functional.classification import binary_calibration_error >>> preds = torch.tensor([0.25, 0.25, 0.55, 0.75, 0.75]) >>> target = torch.tensor([0, 0, 1, 1, 1]) >>> binary_calibration_error(preds, target, n_bins=2, norm='l1') tensor(0.2900) >>> binary_calibration_error(preds, target, n_bins=2, norm='l2') tensor(0.2918) >>> binary_calibration_error(preds, target, n_bins=2, norm='max') tensor(0.3167)
- Return type
multiclass_calibration_error¶
- torchmetrics.functional.classification.multiclass_calibration_error(preds, target, num_classes, n_bins=15, norm='l1', ignore_index=None, validate_args=True)[source]
Computes the Top-label Calibration Error for multiclass tasks. The expected calibration error can be used to quantify how well a given model is calibrated e.g. how well the predicted output probabilities of the model matches the actual probabilities of the ground truth distribution.
Three different norms are implemented, each corresponding to variations on the calibration error metric.
Where is the top-1 prediction accuracy in bin , is the average confidence of predictions in bin , and is the fraction of data points in bin . Bins are constructed in an uniform way in the [0,1] range.
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.- Parameters
num_classes¶ (
int
) – Integer specifing the number of classesn_bins¶ (
int
) – Number of bins to use when computing the metric.norm¶ (
Literal
[‘l1’, ‘l2’, ‘max’]) – Norm used to compare empirical and expected probability bins.ignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.
Example
>>> from torchmetrics.functional.classification import multiclass_calibration_error >>> 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]) >>> multiclass_calibration_error(preds, target, num_classes=3, n_bins=3, norm='l1') tensor(0.2000) >>> multiclass_calibration_error(preds, target, num_classes=3, n_bins=3, norm='l2') tensor(0.2082) >>> multiclass_calibration_error(preds, target, num_classes=3, n_bins=3, norm='max') tensor(0.2333)
- Return type