Class ImageAugmenterBase<T>

Namespace

AiDotNet.Augmentation.Image

Assembly

AiDotNet.dll

Base class for image data augmentations.

public abstract class ImageAugmenterBase<T> : AugmentationBase<T, ImageTensor<T>>, IAugmentation<T, ImageTensor<T>>

Type Parameters

T

The numeric type for calculations.

Inheritance

object

AugmentationBase<T, ImageTensor<T>>

ImageAugmenterBase<T>

Implements

IAugmentation<T, ImageTensor<T>>

Inherited Members

AugmentationBase<T, ImageTensor<T>>.NumOps

AugmentationBase<T, ImageTensor<T>>.OnAugmentationApplied

AugmentationBase<T, ImageTensor<T>>.Name

AugmentationBase<T, ImageTensor<T>>.Probability

AugmentationBase<T, ImageTensor<T>>.IsTrainingOnly

AugmentationBase<T, ImageTensor<T>>.IsEnabled

AugmentationBase<T, ImageTensor<T>>.Apply(ImageTensor<T>, AugmentationContext<T>)

AugmentationBase<T, ImageTensor<T>>.ApplyAugmentation(ImageTensor<T>, AugmentationContext<T>)

AugmentationBase<T, ImageTensor<T>>.GetParameters()

AugmentationBase<T, ImageTensor<T>>.RaiseAugmentationApplied(AugmentationContext<T>, bool)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: Image augmentation transforms images to improve model robustness to variations in viewpoint, lighting, and appearance. Common techniques include:

• Geometric transforms: flips, rotations, scaling, cropping
• Color transforms: brightness, contrast, saturation, hue
• Noise and blur: Gaussian noise, blur, sharpening
• Regularization: cutout, mixup, cutmix

Image data is represented as an ImageTensor with dimensions (height, width, channels).

Constructors

ImageAugmenterBase(double)

Initializes a new image augmentation.

protected ImageAugmenterBase(double probability = 1)

Parameters

probability double

The probability of applying this augmentation (0.0 to 1.0).

Methods

GetChannels(ImageTensor<T>)

Gets the number of channels in the image.

protected int GetChannels(ImageTensor<T> image)

Parameters

image ImageTensor<T>

The input image.

Returns

int

The number of channels (typically 1, 3, or 4).

GetHeight(ImageTensor<T>)

Gets the height of the image.

protected int GetHeight(ImageTensor<T> image)

Parameters

image ImageTensor<T>

The input image.

Returns

int

The height in pixels.

GetWidth(ImageTensor<T>)

Gets the width of the image.

protected int GetWidth(ImageTensor<T> image)

Parameters

image ImageTensor<T>

The input image.

Returns

int

The width in pixels.

HasAlpha(ImageTensor<T>)

Checks if the image has an alpha channel.

protected bool HasAlpha(ImageTensor<T> image)

Parameters

image ImageTensor<T>

The input image.

Returns

bool

True if the image has 4 channels (RGBA).

IsGrayscale(ImageTensor<T>)

Checks if the image is grayscale (single channel).

protected bool IsGrayscale(ImageTensor<T> image)

Parameters

image ImageTensor<T>

The input image.

Returns

bool

True if the image is grayscale.