Interface IAugmentation<T, TData>

Namespace

AiDotNet.Augmentation

Assembly

AiDotNet.dll

Base interface for all data augmentations across domains (image, audio, tabular).

public interface IAugmentation<T, TData>

Type Parameters

T

The numeric type for calculations (e.g., float, double).

TData

The data type being augmented (e.g., ImageTensor, AudioTensor).

Remarks

Augmentations are stochastic transformations applied during training to improve model generalization. Unlike preprocessing transforms, augmentations: - Produce different outputs for the same input (stochastic) - Are typically disabled during inference (training-only) - Have a probability of being applied - Can be composed in pipelines

For Beginners: Augmentation is like creating variations of your training data. If you're training an image classifier, flipping images horizontally gives the model more examples to learn from without collecting new data. This helps the model generalize better to new, unseen data.

Properties

IsEnabled

Gets whether this augmentation is currently enabled.

bool IsEnabled { get; set; }

Property Value

bool

IsTrainingOnly

Gets whether this augmentation should only be applied during training.

bool IsTrainingOnly { get; }

Property Value

bool

Remarks

Most augmentations are training-only. Test-Time Augmentation (TTA) uses specific augmentations during inference to improve predictions.

Name

Gets the name of this augmentation for logging and debugging.

string Name { get; }

Property Value

string

Probability

Gets the probability of this augmentation being applied (0.0 to 1.0).

double Probability { get; }

Property Value

double

Methods

Apply(TData, AugmentationContext<T>?)

Applies the augmentation to the input data.

TData Apply(TData data, AugmentationContext<T>? context = null)

Parameters

data TData

The input data to augment.

context AugmentationContext<T>

The augmentation context containing random state and targets.

Returns

TData

The augmented data.

GetParameters()

Gets the parameters of this augmentation for serialization/logging.

IDictionary<string, object> GetParameters()

Returns

IDictionary<string, object>

A dictionary of parameter names to values.