org.deeplearning4j.nn.params

Class DeconvolutionParamInitializer

java.lang.Object

org.deeplearning4j.nn.params.ConvolutionParamInitializer

org.deeplearning4j.nn.params.DeconvolutionParamInitializer

All Implemented Interfaces:

ParamInitializer

public class DeconvolutionParamInitializer
extends ConvolutionParamInitializer

Field Summary

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

BIAS_KEY, WEIGHT_KEY

Constructor Summary

Constructors

Constructor and Description
DeconvolutionParamInitializer()

Method Summary

Modifier and Type	Method and Description
protected INDArray	createWeightMatrix(NeuralNetConfiguration conf, INDArray weightView, boolean initializeParams)
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 DeconvolutionParamInitializer	getInstance()

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

biasKeys, createBias, 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

DeconvolutionParamInitializer

public DeconvolutionParamInitializer()

Method Detail

getInstance

public static DeconvolutionParamInitializer getInstance()

createWeightMatrix

protected INDArray createWeightMatrix(NeuralNetConfiguration conf,
                                      INDArray weightView,
                                      boolean initializeParams)

Overrides:

createWeightMatrix in class ConvolutionParamInitializer

getGradientsFromFlattened

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

Description copied from interface: ParamInitializer

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 #init(Map, NeuralNetConfiguration, INDArray); 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 ConvolutionParamInitializer

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