MoveAxis

class deeptrack.features.MoveAxis(source: int, destination: int, **kwargs: Any)

Bases: Feature

Moves the axis of the input array or tensor.

This feature rearranges the axes of an input array or tensor, moving a specified source axis to a new destination position. All other axes remain in their original order.

Parameters

source: int

The source position of the axis to move.

destination: int

The destination position of the axis.

**kwargs: Any

Additional keyword arguments passed to the parent Feature class.

Methods

get(inputs, source, destination, **kwargs) -> array or tensor

Move the specified axis of the input to a new position. The input and output can be NumPy arrays or PyTorch tensors.

Examples

>>> import deeptrack as dt

Create an input array:

>>> import numpy as np
>>>
>>> input_array = np.random.rand(2, 3, 4)
>>> input_array.shape
(2, 3, 4)

Apply a MoveAxis feature:

>>> move_axis_feature = dt.MoveAxis(source=0, destination=2)
>>> output_array = move_axis_feature(input_array)
>>> output_array.shape
(3, 4, 2)

Methods Summary

get(inputs, source, destination, **kwargs)

Move the specified axis of the input image to a new position.

Methods Documentation

get(inputs: ndarray | Tensor, source: int, destination: int, **kwargs: Any) → ndarray | Tensor

Move the specified axis of the input image to a new position.

Parameters

inputs: array or tensor

The input image to process. The input can be a NumPy array or a PyTorch tensor.

source: int

The axis to move.

destination: int

The destination position of the axis.

**kwargs: Any

Additional keyword arguments (unused here).

Returns

array or tensor

The input image with the specified axis moved to the destination. The output can be a NumPy array or a PyTorch tensor.