Class FocalLoss<T>

Namespace

AiDotNet.LossFunctions

Assembly

AiDotNet.dll

Implements the Focal Loss function, which gives more weight to hard-to-classify examples.

public class FocalLoss<T> : LossFunctionBase<T>, ILossFunction<T>

Type Parameters

T

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

Inheritance

object

LossFunctionBase<T>

FocalLoss<T>

Implements

ILossFunction<T>

Inherited Members

LossFunctionBase<T>.NumOps

LossFunctionBase<T>.Engine

LossFunctionBase<T>.ValidateVectorLengths(Vector<T>, Vector<T>)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Extension Methods

LossFunctionExtensions.ComputeGradient<T>(ILossFunction<T>, Tensor<T>, Tensor<T>)

LossFunctionExtensions.ComputeLoss<T>(ILossFunction<T>, Tensor<T>, Tensor<T>)

Remarks

For Beginners: Focal Loss was designed to handle class imbalance in classification problems, especially for object detection tasks where background examples vastly outnumber foreground objects.

It modifies the standard cross-entropy loss by adding a factor that reduces the loss contribution from easy-to-classify examples and increases the importance of hard-to-classify examples.

The formula is: -a(1-p)^? * log(p) for positive class -(1-a)p^? * log(1-p) for negative class Where:

• p is the model's estimated probability for the correct class
• a is a weighting factor that balances positive vs negative examples
• ? (gamma) is the focusing parameter that adjusts how much to focus on hard examples

Key properties:

• When ?=0, Focal Loss equals Cross-Entropy Loss
• Higher ? values increase focus on hard-to-classify examples
• a helps handle class imbalance by giving more weight to the minority class

This loss function is ideal for:

• Highly imbalanced datasets
• One-stage object detectors
• Any classification task where easy negatives dominate training

Constructors

FocalLoss(double, double)

Initializes a new instance of the FocalLoss class.

public FocalLoss(double gamma = 2, double alpha = 0.25)

Parameters

gamma double

The focusing parameter that down-weights easy examples. Default is 2.0.

alpha double

The weighting factor for positive class. Default is 0.25.

Methods

CalculateDerivative(Vector<T>, Vector<T>)

Calculates the derivative of the Focal Loss with respect to the predicted values.

public override Vector<T> CalculateDerivative(Vector<T> predicted, Vector<T> actual)

Parameters

predicted Vector<T>

The predicted probabilities from the model.

actual Vector<T>

The actual (target) values (typically 0 or 1).

Returns

Vector<T>

A vector containing the gradient of the loss with respect to each prediction.

CalculateLoss(Vector<T>, Vector<T>)

Calculates the Focal Loss between predicted and actual values.

public override T CalculateLoss(Vector<T> predicted, Vector<T> actual)

Parameters

predicted Vector<T>

The predicted probabilities from the model.

actual Vector<T>

The actual (target) values (typically 0 or 1).

Returns

T

The focal loss value.

CalculateLossAndGradientGpu(IGpuTensor<T>, IGpuTensor<T>)

Calculates both Focal Loss and gradient on GPU in a single efficient pass.

public override (T Loss, IGpuTensor<T> Gradient) CalculateLossAndGradientGpu(IGpuTensor<T> predicted, IGpuTensor<T> actual)

Parameters

predicted IGpuTensor<T>

The predicted GPU tensor from the model.

actual IGpuTensor<T>

The actual (target) GPU tensor.

Returns

(T Loss, IGpuTensor<T> Gradient)

A tuple containing the loss value and gradient tensor.