OneOfDict

class deeptrack.features.OneOfDict(collection: Dict[Any, Feature], key: Any | None = None, **kwargs: Dict[str, Any])

Bases: Feature

Resolve one feature from a dictionary.

This feature selects one feature from a dictionary of features and applies it to the input. By default, the selection is made randomly from the dictionary’s values, but it can be controlled by specifying a key.

Its default behaviour is to sample the values diction uniformly random. This can be controlled by the key argument, where the feature resolved is chosen as collection[key].

Parameters

collectionDict[Any, Feature]

A dictionary where keys are identifiers and values are features to choose from.

keyOptional[Any], optional

The key of the feature to resolve from the dictionary. If not provided, a key is selected randomly.

**kwargsDict[str, Any]

Additional keyword arguments passed to the parent Feature class.

Attributes

collectionDict[Any, Feature]

The dictionary of features to choose from.

Methods

get(image, key, _ID=(), **kwargs)

Resolves the selected feature from the dictionary and applies it to the input image.

Example

>>> import numpy as np
>>> from deeptrack.features import OneOfDict, Add, Multiply

Create a dictionary of features:

>>> features_dict = {
...     "add": Add(value=10),
...     "multiply": Multiply(value=2),
... }
>>> one_of_dict_feature = OneOfDict(features_dict)

Apply the feature randomly to an input image:

>>> input_image = np.array([1, 2, 3])
>>> output_image = one_of_dict_feature(input_image)
>>> print(output_image)  # Output depends on randomly selected feature.

Specify a key to control the selected feature:

>>> controlled_feature = OneOfDict(features_dict, key="add")
>>> output_image = controlled_feature(input_image)
>>> print(output_image)  # Adds 10 to each element.

Methods Summary

get(image, key[, _ID])

Resolve selected feature and applies it to the input image.

Methods Documentation

get(image: Any, key: Any, _ID: Tuple[int, ...] = (), **kwargs: Dict[str, Any]) → Any

Resolve selected feature and applies it to the input image.

This method resolves the selected feature from the dictionary and applies it to the input image.

Parameters

imageAny

The input image to process.

keyAny

The key of the feature to apply from the dictionary.

_IDTuple[int, …], optional

A unique identifier for caching and parallel processing.

**kwargsAny

Additional keyword arguments.

Returns

Any

The output of the selected feature applied to the input image.