org.deeplearning4j.nn.params

Class EmbeddingLayerParamInitializer

java.lang.Object

org.deeplearning4j.nn.params.DefaultParamInitializer

org.deeplearning4j.nn.params.EmbeddingLayerParamInitializer

All Implemented Interfaces:

ParamInitializer

public class EmbeddingLayerParamInitializer
extends DefaultParamInitializer

Parameter initializer for EmbeddingLayer and EmbeddingSequenceLayer

Author:

Alex Black

Field Summary

Fields inherited from class org.deeplearning4j.nn.params.DefaultParamInitializer

BIAS_KEY, GAIN_KEY, WEIGHT_KEY

Constructor Summary

Constructors

Constructor and Description
EmbeddingLayerParamInitializer()

Method Summary

Modifier and Type	Method and Description
protected INDArray	createWeightMatrix(long nIn, long nOut, IWeightInit weightInit, INDArray weightParamView, boolean initializeParameters)
static EmbeddingLayerParamInitializer	getInstance()

Methods inherited from class org.deeplearning4j.nn.params.DefaultParamInitializer

biasKeys, createBias, createBias, createGain, createGain, createWeightMatrix, getGradientsFromFlattened, hasBias, hasLayerNorm, init, isBiasParam, isWeightParam, numParams, numParams, paramKeys, weightKeys

Methods inherited from class java.lang.Object

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

Constructor Detail

EmbeddingLayerParamInitializer

public EmbeddingLayerParamInitializer()

Method Detail

getInstance

public static EmbeddingLayerParamInitializer getInstance()

createWeightMatrix

protected INDArray createWeightMatrix(long nIn,
                                      long nOut,
                                      IWeightInit weightInit,
                                      INDArray weightParamView,
                                      boolean initializeParameters)

Overrides:

createWeightMatrix in class DefaultParamInitializer