ObjectModel

class btrack.models.ObjectModel(*, states: int, emission: ndarray[tuple[Any, ...], dtype[_ScalarT]], transition: ndarray[tuple[Any, ...], dtype[_ScalarT]], start: ndarray[tuple[Any, ...], dtype[_ScalarT]], name: str = 'Default')

Bases: BaseModel

The btrack object model.

This is a class to deal with state transitions in the object, essentially a Hidden Markov Model. Makes an assumption that the states are all observable, but with noise.

Parameters:

namestr

A name identifier for the model.

emissionarray

The emission probability matrix.

transitionarray

Transition probabilities.

startarray

Initial probabilities.

statesint

Number of observable states.

Attributes Summary

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Methods Summary

parse_array(v, info)
reshape_emission_transition(v, info)
reshape_start(v, info)

Attributes Documentation

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True, 'json_encoders': {<class 'numpy.ndarray'>: <function ObjectModel.<lambda>>}, 'validate_assignment': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Methods Documentation

classmethod parse_array(v, info)

classmethod reshape_emission_transition(v, info)

classmethod reshape_start(v, info)