Unsqueeze

class deeptrack.features.Unsqueeze(axis: int | Tuple[int, ...] | None = -1, **kwargs: Dict[str, Any])

Bases: Feature

Unsqueezes the input image to the smallest possible dimension.

This feature adds new singleton dimensions to the input image at the specified axis or axes. If no axis is specified, it defaults to adding a singleton dimension at the last axis.

Parameters

axisint or Tuple[int, …], optional

The axis or axes where new singleton dimensions should be added. Defaults to None, which adds a singleton dimension at the last axis.

**kwargsDict[str, Any]

Additional keyword arguments passed to the parent Feature class.

Example

>>> import numpy as np
>>> from deeptrack.features import Unsqueeze

Create an input array:

>>> input_image = np.array([1, 2, 3])
>>> print(input_image.shape)
(3,)

Apply an Unsqueeze feature:

>>> unsqueeze_feature = Unsqueeze(axis=0)
>>> output_image = unsqueeze_feature(input_image)
>>> print(output_image.shape)
(1, 3)

Without specifying an axis:

>>> unsqueeze_feature = Unsqueeze()
>>> output_image = unsqueeze_feature(input_image)
>>> print(output_image.shape)
(3, 1)

Methods Summary

get(image[, axis])

Add singleton dimensions to the input image.

Methods Documentation

get(image: ndarray, axis: int | Tuple[int, ...] | None = -1, **kwargs: Dict[str, Any]) → ndarray

Add singleton dimensions to the input image.

Parameters

imagenp.ndarray

The input image to process.

axisint or Tuple[int, …], optional

The axis or axes where new singleton dimensions should be added. Defaults to -1, which adds a singleton dimension at the last axis.

**kwargsDict[str, Any]

Additional keyword arguments (unused here).

Returns

np.ndarray

The input image with the specified singleton dimensions added.