org.deeplearning4j.nn.params

Class ElementWiseParamInitializer

java.lang.Object

org.deeplearning4j.nn.params.DefaultParamInitializer

org.deeplearning4j.nn.params.ElementWiseParamInitializer

All Implemented Interfaces:

ParamInitializer

public class ElementWiseParamInitializer
extends DefaultParamInitializer

created by jingshu

Field Summary

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

BIAS_KEY, GAIN_KEY, WEIGHT_KEY

Constructor Summary

Constructors

Constructor and Description
ElementWiseParamInitializer()

Method Summary

Modifier and Type	Method and Description
protected INDArray	createWeightMatrix(long nIn, long nOut, IWeightInit weightInit, INDArray weightParamView, boolean initializeParameters)
Map<String,INDArray>	getGradientsFromFlattened(NeuralNetConfiguration conf, INDArray gradientView) Return a map of gradients (in their standard non-flattened representation), taken from the flattened (row vector) gradientView array.
static ElementWiseParamInitializer	getInstance()
Map<String,INDArray>	init(NeuralNetConfiguration conf, INDArray paramsView, boolean initializeParams) Initialize the parameters
long	numParams(Layer layer)

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

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

Methods inherited from class java.lang.Object

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

Constructor Detail

ElementWiseParamInitializer

public ElementWiseParamInitializer()

Method Detail

getInstance

public static ElementWiseParamInitializer getInstance()

numParams

public long numParams(Layer layer)

Specified by:

numParams in interface ParamInitializer

Overrides:

numParams in class DefaultParamInitializer

init

public Map<String,INDArray> init(NeuralNetConfiguration conf,
                                 INDArray paramsView,
                                 boolean initializeParams)

Initialize the parameters

Specified by:

init in interface ParamInitializer

Overrides:

init in class DefaultParamInitializer

Parameters:

conf - the configuration

paramsView - a view of the full network (backprop) parameters

initializeParams - if true: initialize the parameters according to the configuration. If false: don't modify the values in the paramsView array (but do select out the appropriate subset, reshape etc as required)

Returns:

Map of parameters keyed by type (view of the 'paramsView' array)

getGradientsFromFlattened

public Map<String,INDArray> getGradientsFromFlattened(NeuralNetConfiguration conf,
                                                      INDArray gradientView)

Return a map of gradients (in their standard non-flattened representation), taken from the flattened (row vector) gradientView array. The idea is that operates in exactly the same way as the paramsView does in thus the position in the view (and, the array orders) must match those of the parameters

Specified by:

getGradientsFromFlattened in interface ParamInitializer

Overrides:

getGradientsFromFlattened in class DefaultParamInitializer

Parameters:

conf - Configuration

gradientView - The flattened gradients array, as a view of the larger array

Returns:

A map containing an array by parameter type, that is a view of the full network gradients array

createWeightMatrix

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

Overrides:

createWeightMatrix in class DefaultParamInitializer