org.deeplearning4j.nn.params

Class BatchNormalizationParamInitializer

java.lang.Object

org.deeplearning4j.nn.params.BatchNormalizationParamInitializer

All Implemented Interfaces:

ParamInitializer

public class BatchNormalizationParamInitializer
extends java.lang.Object
implements ParamInitializer

Batch normalization variable init

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String	BETA
static java.lang.String	GAMMA
static java.lang.String	GLOBAL_MEAN
static java.lang.String	GLOBAL_VAR

Constructor Summary

Constructors

Constructor and Description
BatchNormalizationParamInitializer()

Method Summary

Modifier and Type	Method and Description
java.util.Map<java.lang.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.
static BatchNormalizationParamInitializer	getInstance()
java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>	init(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray paramView, boolean initializeParams) Initialize the parameters
int	numParams(NeuralNetConfiguration conf)

Methods inherited from class java.lang.Object

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

Field Detail

GAMMA

public static final java.lang.String GAMMA

See Also:

Constant Field Values

BETA

public static final java.lang.String BETA

See Also:

Constant Field Values

GLOBAL_MEAN

public static final java.lang.String GLOBAL_MEAN

See Also:

Constant Field Values

GLOBAL_VAR

public static final java.lang.String GLOBAL_VAR

See Also:

Constant Field Values

Constructor Detail

BatchNormalizationParamInitializer

public BatchNormalizationParamInitializer()

Method Detail

getInstance

public static BatchNormalizationParamInitializer getInstance()

numParams

public int numParams(NeuralNetConfiguration conf)

Specified by:

numParams in interface ParamInitializer

init

public java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> init(NeuralNetConfiguration conf,
                                                                                 org.nd4j.linalg.api.ndarray.INDArray paramView,
                                                                                 boolean initializeParams)

Description copied from interface: ParamInitializer

Initialize the parameters

Specified by:

init in interface ParamInitializer

Parameters:

conf - the configuration

paramView - 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 java.util.Map<java.lang.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 #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