OneHot

class deeptrack.features.OneHot(num_classes: int | Callable[[...], int], **kwargs: Any)

Bases: Feature

Convert the input to a one-hot encoded array.

This feature takes an input array of integer class labels and converts it into a one-hot encoded array. The last dimension of the input is replaced by the one-hot encoding.

Parameters

num_classes: PropertyLike[int]

The total number of classes for the one-hot encoding.

**kwargs: Any

Additional keyword arguments passed to the parent Feature class.

Methods

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

Convert the input array of class labels into a one-hot encoded array. The input and output can be NumPy arrays or PyTorch tensors.

Examples

>>> import deeptrack as dt

Create an input array of class labels:

>>> import numpy as np
>>>
>>> input_data = np.array([0, 1, 2])

Apply a OneHot feature:

>>> one_hot_feature = dt.OneHot(num_classes=3)
>>> one_hot_encoded = one_hot_feature.get(input_data, num_classes=3)
>>> one_hot_encoded
array([[1., 0., 0.],
       [0., 1., 0.],
       [0., 0., 1.]], dtype=float32)

Methods Summary

get(image, num_classes, **kwargs)

Convert the input array of labels into a one-hot encoded array.

Methods Documentation

get(image: ndarray | Tensor, num_classes: int, **kwargs: Any) → ndarray | Tensor

Convert the input array of labels into a one-hot encoded array.

Parameters

image: array or tensor

The input array of class labels. The last dimension should contain integers representing class indices. The input can be a NumPy array or a PyTorch tensor.

num_classes: int

The total number of classes for the one-hot encoding.

**kwargs: Any

Additional keyword arguments (unused here).

Returns

array or tensor

The one-hot encoded array. The last dimension is replaced with one-hot vectors of length num_classes. The output can be a NumPy array or a PyTorch tensor. In all cases, it is of data type float32 (e.g., np.float32 or torch.float32).