Class TemporalCrop<T>

Namespace

AiDotNet.Augmentation.Video

Assembly

AiDotNet.dll

Randomly crops a temporal segment from video.

public class TemporalCrop<T> : TemporalAugmenterBase<T>, IAugmentation<T, ImageTensor<T>[]>

Type Parameters

T

The numeric type for calculations.

Inheritance

object

AugmentationBase<T, ImageTensor<T>[]>

VideoAugmenterBase<T>

TemporalAugmenterBase<T>

TemporalCrop<T>

Implements

IAugmentation<T, ImageTensor<T>[]>

Inherited Members

VideoAugmenterBase<T>.FrameRate

VideoAugmenterBase<T>.GetDuration(ImageTensor<T>[])

VideoAugmenterBase<T>.GetFrameCount(ImageTensor<T>[])

VideoAugmenterBase<T>.ValidateFrameDimensions(ImageTensor<T>[])

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: Temporal cropping takes a random consecutive portion of the video. For example, from a 10-second video, it might extract 8 seconds starting at a random point. This helps models learn to recognize actions regardless of when they occur in the video.

When to use:

• Action recognition where action can occur anywhere in the video
• Training with variable-length videos
• Reducing overfitting to specific temporal positions

Constructors

TemporalCrop(double, double, double, double)

Creates a new temporal crop augmentation.

public TemporalCrop(double minCropRatio = 0.7, double maxCropRatio = 0.9, double probability = 0.5, double frameRate = 30)

Parameters

minCropRatio double

Minimum fraction of frames to keep (default: 0.7).

maxCropRatio double

Maximum fraction of frames to keep (default: 0.9).

probability double

Probability of applying this augmentation (default: 0.5).

frameRate double

Frame rate of the video (default: 30).

Properties

MaxCropRatio

Gets the maximum crop ratio (fraction of original length to keep).

public double MaxCropRatio { get; }

Property Value

double

Remarks

Default: 0.9 (keep at most 90% of frames)

MinCropRatio

Gets the minimum crop ratio (fraction of original length to keep).

public double MinCropRatio { get; }

Property Value

double

Remarks

Default: 0.7 (keep at least 70% of frames)

Methods

ApplyAugmentation(ImageTensor<T>[], AugmentationContext<T>)

Implement this method to perform the actual augmentation.

protected override ImageTensor<T>[] ApplyAugmentation(ImageTensor<T>[] data, AugmentationContext<T> context)

Parameters

data ImageTensor<T>[]

The input data.

context AugmentationContext<T>

The augmentation context.

Returns

ImageTensor<T>[]

The augmented data.

GetParameters()

Gets the parameters of this augmentation.

public override IDictionary<string, object> GetParameters()

Returns

IDictionary<string, object>

A dictionary of parameter names to values.