Package ai.djl.training.initializer

Class UniformInitializer

java.lang.Object

ai.djl.training.initializer.UniformInitializer

All Implemented Interfaces:

Initializer

public class UniformInitializer
extends Object
implements Initializer

UniformInitializer initializes weights with random values uniformly sampled from a given range.

Field Summary

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

ONES, ZEROS

Constructor Summary

Constructors

Constructor	Description
UniformInitializer()	Creates an instance of UniformInitializer with a default scale of 0.07.
UniformInitializer(float scale)	Initializes a uniform 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

UniformInitializer

public UniformInitializer()

Creates an instance of UniformInitializer with a default scale of 0.07.

UniformInitializer

public UniformInitializer(float scale)

Initializes a uniform initializer.

Parameters:

scale - the bound on the range of the generated random values. Values are generated from the range [-`scale`, `scale`]. Default scale is 0.07.

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