fl4health.metrics.base_metrics module¶

class Metric(name)[source]¶

Bases: ABC

__init__(name)[source]¶

Base abstract Metric class to extend for metric accumulation and computation.

abstract clear()[source]¶

Resets metric.

Raises:: NotImplementedError – To be defined in the classes expending this class.
Return type:: None

abstract compute(name=None)[source]¶

Compute metric on state accumulated over updates.

Parameters:: name (str | None) – Optional name used in conjunction with class attribute name to define key in metrics dictionary.
Raises:: NotImplementedError – To be defined in the classes extending this class.
Returns:: A dictionary of string and Scalar representing the computed metric and its associated key.
Return type:: Metrics

abstract update(input, target)[source]¶

This method updates the state of the metric by appending the passed input and target pairing to their respective list.

Parameters:

input (torch.Tensor) – The predictions of the model to be evaluated.
target (torch.Tensor) – The ground truth target to evaluate predictions against.

Raises:

NotImplementedError – To be defined in the classes extending this class.

Return type:

None

class MetricPrefix(value)[source]¶

Bases: Enum

An enumeration.