Class DecayLearningRate

Namespace

NeuralNetworks.LearningRates

Assembly

NeuralNetworks.dll

public abstract class DecayLearningRate : LearningRate

Inheritance

object

LearningRate

DecayLearningRate

Derived

CosineDecayLearningRate

ExponentialDecayLearningRate

LinearDecayLearningRate

Inherited Members

LearningRate.Update(int, int, int)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

DecayLearningRate(float, int)

protected DecayLearningRate(float initialLearningRate, int warmupSteps = 0)

Parameters

initialLearningRate float

warmupSteps int

Properties

CurrentLearningRate

protected float CurrentLearningRate { get; set; }

Property Value

float

InitialLearningRate

protected float InitialLearningRate { get; }

Property Value

float

WarmupSteps

public int WarmupSteps { get; init; }

Property Value

int

Methods

ApplyWarmup(int)

protected void ApplyWarmup(int steps)

Parameters

steps int

GetLearningRate()

public override float GetLearningRate()

Returns

float