org.deeplearning4j.nn.api

Interface ParamInitializer

All Known Implementing Classes:

BatchNormalizationParamInitializer, BidirectionalParamInitializer, CenterLossParamInitializer, Convolution3DParamInitializer, ConvolutionParamInitializer, Deconvolution3DParamInitializer, DeconvolutionParamInitializer, DefaultParamInitializer, DepthwiseConvolutionParamInitializer, ElementWiseParamInitializer, EmbeddingLayerParamInitializer, EmptyParamInitializer, FrozenLayerParamInitializer, FrozenLayerWithBackpropParamInitializer, GravesBidirectionalLSTMParamInitializer, GravesLSTMParamInitializer, LSTMParamInitializer, OCNNParamInitializer, PReLUParamInitializer, PretrainParamInitializer, SameDiffParamInitializer, SeparableConvolutionParamInitializer, SimpleRnnParamInitializer, VariationalAutoencoderParamInitializer, WrapperLayerParamInitializer

public interface ParamInitializer

Param initializer for a layer

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
List<String>	biasKeys(Layer layer) Bias parameter keys given the layer configuration
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.
Map<String,INDArray>	init(NeuralNetConfiguration conf, INDArray paramsView, boolean initializeParams) Initialize the parameters
boolean	isBiasParam(Layer layer, String key) Is the specified parameter a bias?
boolean	isWeightParam(Layer layer, String key) Is the specified parameter a weight?
long	numParams(Layer layer)
long	numParams(NeuralNetConfiguration conf)
List<String>	paramKeys(Layer layer) Get a list of all parameter keys given the layer configuration
List<String>	weightKeys(Layer layer) Weight parameter keys given the layer configuration

Method Detail

numParams

long numParams(NeuralNetConfiguration conf)

numParams

long numParams(Layer layer)

paramKeys

List<String> paramKeys(Layer layer)

Get a list of all parameter keys given the layer configuration

Parameters:

layer - Layer

Returns:

All parameter keys

weightKeys

List<String> weightKeys(Layer layer)

Weight parameter keys given the layer configuration

Parameters:

layer - Layer

Returns:

Weight parameter keys

biasKeys

List<String> biasKeys(Layer layer)

Bias parameter keys given the layer configuration

Parameters:

layer - Layer

Returns:

Bias parameter keys

isWeightParam

boolean isWeightParam(Layer layer,
                      String key)

Is the specified parameter a weight?

Parameters:

layer - Layer

key - Key to check

Returns:

True if parameter is a weight

isBiasParam

boolean isBiasParam(Layer layer,
                    String key)

Is the specified parameter a bias?

Parameters:

layer - Layer

key - Key to check

Returns:

True if parameter is a bias

init

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

Initialize the parameters

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

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 #init(Map, NeuralNetConfiguration, INDArray); thus the position in the view (and, the array orders) must match those of the parameters

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