Package ai.djl.training.initializer

Class NormalInitializer

java.lang.Object

ai.djl.training.initializer.NormalInitializer

All Implemented Interfaces:

Initializer

public class NormalInitializer
extends Object
implements Initializer

NormalInitializer initializes weights with random values sampled from a normal distribution with a mean of zero and standard deviation of sigma. Default standard deviation is 0.01.

Field Summary

Fields inherited from interface ai.djl.training.initializer.Initializer

ONES, ZEROS

Constructor Summary

Constructors

Constructor	Description
NormalInitializer()	Creates an instance of NormalInitializer with a default sigma of 0.01.
NormalInitializer(float sigma)	Creates a Normal initializer.

Method Summary

Modifier and Type	Method	Description
NDArray	initialize(NDManager manager, Shape shape, DataType dataType)	Initializes a single NDArray.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

NormalInitializer

public NormalInitializer()

Creates an instance of NormalInitializer with a default sigma of 0.01.

NormalInitializer

public NormalInitializer(float sigma)

Creates a Normal initializer.

Parameters:

sigma - the standard deviation of the normal distribution

Method Details

initialize

public NDArray initialize(NDManager manager,
 Shape shape,
 DataType dataType)

Initializes a single NDArray.

Specified by:

initialize in interface Initializer

Parameters:

manager - the NDManager to create the new NDArray in

shape - the Shape for the new NDArray

dataType - the DataType for the new NDArray

Returns:

the NDArray initialized with the manager and shape