Combine

class deeptrack.features.Combine(features: list[Feature], **kwargs: Any)

Bases: StructuralFeature

Combine multiple features into a single feature.

This feature applies a list of features to the same input and returns their outputs as a list. It is useful for computing multiple parallel outputs from the same data (e.g., branches in a feature graph).

Parameters

features: list[Feature]

A list of features to combine. Each feature will be applied in order, and their outputs collected into a list.

**kwargs: Any

Additional keyword arguments passed to the parent StructuralFeature class.

Methods

get(inputs, **kwargs) -> list[Any]

Resolves each feature in the features list on the inputs and returns their results as a list.

Examples

>>> import deeptrack as dt

Define a list of features:

>>> add_1 = dt.Add(b=1)
>>> add_2 = dt.Add(b=2)
>>> add_3 = dt.Add(b=3)

Combine the features:

>>> combined_feature = dt.Combine([add_1, add_2, add_3])

Define an input image:

>>> import numpy as np
>>>
>>> input_image = np.zeros((2, 3))

Apply the combined feature:

>>> output_list = combined_feature(input_image)
>>> output_list
[array([[1., 1., 1.],
        [1., 1., 1.]]),
 array([[2., 2., 2.],
        [2., 2., 2.]]),
 array([[3., 3., 3.],
        [3., 3., 3.]])]

Methods Summary

get(inputs, **kwargs)

Resolve each feature in the features list on the inputs.

Methods Documentation

get(inputs: Any, **kwargs: Any) → list[Any]

Resolve each feature in the features list on the inputs.

Parameters

image: Any

The input or list of inputs to process.

**kwargs: Any

Additional arguments passed to each feature’s resolve method.

Returns

list[Any]

A list containing the outputs of each feature applied to the input.