Class BatchNormalization

Batch normalization layer (Ioffe and Szegedy, 2014). Normalize the activations of the previous layer at each batch, i.e.applies a transformation that maintains the mean activation close to 0 and the activation standard deviation close to 1.

Inheritance

System.Object

Keras

Base

BaseLayer

BatchNormalization

Implements

System.IDisposable

Inherited Members

BaseLayer.Set(BaseLayer[])

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.Layers

Assembly: Keras.dll

Syntax

public class BatchNormalization : BaseLayer, IDisposable

Constructors

BatchNormalization(Int32, Single, Single, Boolean, Boolean, String, String, String, String, String, String, String, String)

Initializes a new instance of the BatchNormalization class.

Declaration

public BatchNormalization(int axis = -1, float momentum = 0.99F, float epsilon = 0.001F, bool center = true, bool scale = true, string beta_initializer = "zeros", string gamma_initializer = "ones", string moving_mean_initializer = "zeros", string moving_variance_initializer = "ones", string beta_regularizer = "", string gamma_regularizer = "", string beta_constraint = "", string gamma_constraint = "")

Parameters

Type	Name	Description
System.Int32	axis	Integer, the axis that should be normalized (typically the features axis). For instance, after a Conv2D layer with data_format="channels_first", set axis=1 in BatchNormalization.
System.Single	momentum	Momentum for the moving mean and the moving variance.
System.Single	epsilon	Small float added to variance to avoid dividing by zero.
System.Boolean	center	If True, add offset of beta to normalized tensor. If False, beta is ignored.
System.Boolean	scale	If True, multiply by gamma. If False, gamma is not used. When the next layer is linear (also e.g. nn.relu), this can be disabled since the scaling will be done by the next layer.
System.String	beta_initializer	Initializer for the beta weight.
System.String	gamma_initializer	Initializer for the gamma weight.
System.String	moving_mean_initializer	Initializer for the moving mean.
System.String	moving_variance_initializer	Initializer for the moving variance.
System.String	beta_regularizer	Optional regularizer for the beta weight.
System.String	gamma_regularizer	Optional regularizer for the gamma weight.
System.String	beta_constraint	Optional constraint for the beta weight.
System.String	gamma_constraint	Optional constraint for the gamma weight

Implements

System.IDisposable