org.deeplearning4j.nn.params

Class DefaultParamInitializer

java.lang.Object

org.deeplearning4j.nn.params.DefaultParamInitializer

All Implemented Interfaces:

ParamInitializer

Direct Known Subclasses:

PretrainParamInitializer

public class DefaultParamInitializer
extends Object
implements ParamInitializer

Static weight initializer with just a weight matrix and a bias

Author:

Adam Gibson

Field Summary

Fields

Modifier and Type	Field and Description
static String	BIAS_KEY
static String	WEIGHT_KEY

Constructor Summary

Constructors

Constructor and Description
DefaultParamInitializer()

Method Summary

Modifier and Type	Method and Description
protected org.nd4j.linalg.api.ndarray.INDArray	createBias(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray biasParamView)
protected org.nd4j.linalg.api.ndarray.INDArray	createWeightMatrix(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray weightParamView)
Map<String,org.nd4j.linalg.api.ndarray.INDArray>	getGradientsFromFlattened(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray gradientView) Return a map of gradients (in their standard non-flattened representation), taken from the flattened (row vector) gradientView array.
void	init(Map<String,org.nd4j.linalg.api.ndarray.INDArray> params, NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray paramsView) Initialize the parameters
int	numParams(NeuralNetConfiguration conf, boolean backprop)

Methods inherited from class java.lang.Object

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

Field Detail

WEIGHT_KEY

public static final String WEIGHT_KEY

See Also:

Constant Field Values

BIAS_KEY

public static final String BIAS_KEY

See Also:

Constant Field Values

Constructor Detail

DefaultParamInitializer

public DefaultParamInitializer()

Method Detail

numParams

public int numParams(NeuralNetConfiguration conf,
                     boolean backprop)

Specified by:

numParams in interface ParamInitializer

init

public void init(Map<String,org.nd4j.linalg.api.ndarray.INDArray> params,
                 NeuralNetConfiguration conf,
                 org.nd4j.linalg.api.ndarray.INDArray paramsView)

Description copied from interface: ParamInitializer

Initialize the parameters

Specified by:

init in interface ParamInitializer

Parameters:

params - the map (initially empty) that will contain a view of the 'paramsView' array

conf - the configuration

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

getGradientsFromFlattened

public Map<String,org.nd4j.linalg.api.ndarray.INDArray> getGradientsFromFlattened(NeuralNetConfiguration conf,
                                                                                  org.nd4j.linalg.api.ndarray.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 the paramsView does in ParamInitializer.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

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

createBias

protected org.nd4j.linalg.api.ndarray.INDArray createBias(NeuralNetConfiguration conf,
                                                          org.nd4j.linalg.api.ndarray.INDArray biasParamView)

createWeightMatrix

protected org.nd4j.linalg.api.ndarray.INDArray createWeightMatrix(NeuralNetConfiguration conf,
                                                                  org.nd4j.linalg.api.ndarray.INDArray weightParamView)