Transpose

class deeptrack.features.Transpose(axes: tuple[int, ...] | None = None, **kwargs: dict[str, Any])

Bases: Feature

Transpose the input image.

This feature rearranges the axes of an input image according to the specified order. The axes parameter determines the new order of the dimensions.

Parameters

axes: tuple[int, …], optional

A tuple specifying the permutation of the axes. If None, the axes are reversed by default.

**kwargs:: dict of str to Any

Additional keyword arguments passed to the parent Feature class.

Methods

get(image: np.ndarray, axes: tuple[int, …] | None, **kwargs: dict[str, Any]) -> np.ndarray

Transpose the axes of the input image

Examples

>>> import deeptrack as dt
>>> import numpy as np

Create an input array: >>> input_image = np.random.rand(2, 3, 4) >>> print(input_image.shape) (2, 3, 4)

Apply a Transpose feature: >>> transpose_feature = dt.Transpose(axes=(1, 2, 0)) >>> output_image = transpose_feature(input_image) >>> print(output_image.shape) (3, 4, 2)

Without specifying axes: >>> transpose_feature = dt.Transpose() >>> output_image = transpose_feature(input_image) >>> print(output_image.shape) (4, 3, 2)

Methods Summary

get(image[, axes])

Transpose the axes of the input image.

Methods Documentation

get(image: np.ndarray, axes: tuple[int, ...] | None = None, **kwargs: dict[str, Any]) → np.ndarray

Transpose the axes of the input image.

Parameters

image: np.ndarray

The input image to process.

axes: tuple[int, …], optional

A tuple specifying the permutation of the axes. If None, the axes are reversed by default.

**kwargs: Any

Additional keyword arguments (unused here).

Returns

np.ndarray

The transposed image with rearranged axes.