Class Adam

Adam optimizer. Default parameters follow those provided in the original paper.

Inheritance

System.Object

Keras

Base

Adam

Implements

System.IDisposable

Inherited Members

Base.Parameters

Base.None

Base.Init()

Base.ToPython()

Base.InvokeStaticMethod(Object, String, Dictionary<String, Object>)

Base.InvokeMethod(String, Dictionary<String, Object>)

Base.Item[String]

Keras.Instance

Keras.keras

Keras.keras2onnx

Keras.tfjs

Keras.Dispose()

Keras.ToTuple(Array)

Keras.ToList(Array)

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: Keras.Optimizers

Assembly: Keras.dll

Syntax

public class Adam : Base, IDisposable

Constructors

Adam(Single, Single, Single, Nullable<Single>, Single, Boolean)

Initializes a new instance of the Adam class.

Declaration

public Adam(float lr = 0.001F, float beta_1 = 0.9F, float beta_2 = 0.999F, float? epsilon = default(float? ), float decay = 0F, bool amsgrad = false)

Parameters

Type	Name	Description
System.Single	lr	The lr.
System.Single	beta_1	The beta 1.
System.Single	beta_2	The beta 2.
System.Nullable<System.Single>	epsilon	The epsilon.
System.Single	decay	The decay.
System.Boolean	amsgrad	boolean. Whether to apply the AMSGrad variant of this algorithm from the paper "On the Convergence of Adam and Beyond".

Implements

System.IDisposable