sportslabkit.mot.base

Overview

Classes

Callback	Base class for creating new callbacks.
MultiObjectTracker	Helper class that provides a standard way to create an ABC using

Function

with_callbacks(func)

Decorator for wrapping methods that require callback invocations.

Classes

class sportslabkit.mot.base.Callback

Base class for creating new callbacks.

This class defines the basic structure of a callback and allows for dynamic method creation for handling different events in the Trainer’s lifecycle.

__getattr__(name

str) -> callable: Returns a dynamically created method based on the given name.

class sportslabkit.mot.base.MultiObjectTracker(window_size=1, step_size=None, max_staleness=5, min_length=5, callbacks=None)

Bases: abc.ABC

Helper class that provides a standard way to create an ABC using inheritance.

Overview

Methods

update_tracklet(tracklet, states)	-
update(current_frame, trackelts)	abc -
process_sequence_item(sequence)	-
track(sequence)	-
track_sequence(sequence)	-
cleanup_tracklets(tracklets)	-
increment_staleness(tracklets)	-
reset_staleness(tracklets)	-
pre_track()	-
post_track()	-
reset()	-
check_updated_state(state)	-
create_tracklet(state)	-
to_bbdf()	Create a bounding box dataframe.
separate_stale_tracklets(unassigned_tracklets)	-
create_hparam_dict()	-
get_new_hyperparameters(hparams, trial)	-
apply_hyperparameters(params)	-
tune_hparams(frames_list, bbdf_gt_list, n_trials, hparam_search_space, verbose, return_study, use_bbdf, reuse_detections, sampler, pruner)	-

Members

update_tracklet(tracklet: sportslabkit.Tracklet, states: dict[str, Any])

abstract update(current_frame: Any, trackelts: list[sportslabkit.Tracklet]) → tuple[list[sportslabkit.Tracklet], list[dict[str, Any]]]

process_sequence_item(sequence: Any)

track(sequence: Iterable[Any] | np.ndarray) → sportslabkit.Tracklet

track_sequence(sequence)

cleanup_tracklets(tracklets)

increment_staleness(tracklets)

reset_staleness(tracklets)

pre_track()

post_track()

reset()

check_updated_state(state: dict[str, Any])

create_tracklet(state: dict[str, Any])

to_bbdf()

Create a bounding box dataframe.

separate_stale_tracklets(unassigned_tracklets)

create_hparam_dict()

get_new_hyperparameters(hparams, trial)

apply_hyperparameters(params)

tune_hparams(frames_list, bbdf_gt_list, n_trials=100, hparam_search_space=None, verbose=False, return_study=False, use_bbdf=False, reuse_detections=False, sampler=None, pruner=None)

Functions

sportslabkit.mot.base.with_callbacks(func)

Decorator for wrapping methods that require callback invocations.

Parameters:

func (callable) – The method to wrap.

Returns:

The wrapped method.

Return type:

callable