Metric

class maite.protocols.multiobject_tracking.Metric(*args, **kwargs)

A metric protocol for the multi-object tracking AI problem.

A metric in this sense is expected to measure the level of agreement between model predictions and ground-truth labels.

Attributes:

metadataMetricMetadata

A typed dictionary containing at least an ‘id’ field of type str

Methods

update(pred_batch: Sequence[MultiobjectTrackingTarget], target_batch: Sequence[MultiobjectTrackingTarget], metadata_batch: Sequence[DatumMetadata]) -> None	Add predictions and targets (and metadata if applicable) to metric’s cache for later calculation.
compute() -> Mapping[str, Any]	Compute metric value(s) for currently cached predictions and targets, returned as a read-only mapping.
reset() -> None	Clear contents of current metric’s cache of predictions and targets.