Model

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

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

Implementers must provide a __call__ method that operates on a batch of model inputs (as Sequence [VideoStream]) and returns a batch of model targets (as Sequence [MultiobjectTrackingTarget])

Attributes:

metadataModelMetadata

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

Methods

__call__(input_batch: Sequence[VideoStream]) -> Sequence[MultiobjectTrackingTarget]

Make a model prediction for inputs in input batch. Input batch is expected to be Sequence [VideoStream]. Target batch is expected to be Sequence [MultiobjectTrackingTarget].