org.deeplearning4j.nn.api

Interface ParamInitializer

All Known Implementing Classes:

BatchNormalizationParamInitializer, ConvolutionParamInitializer, DefaultParamInitializer, EmptyParamInitializer, GravesBidirectionalLSTMParamInitializer, GravesLSTMParamInitializer, GRUParamInitializer, PretrainParamInitializer

public interface ParamInitializer

Param initializer for a layer

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
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> paramsMap, NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray paramsView, boolean initializeParams) Initialize the parameters
int	numParams(NeuralNetConfiguration conf, boolean backprop)

Method Detail

numParams

int numParams(NeuralNetConfiguration conf,
              boolean backprop)

init

void init(Map<String,org.nd4j.linalg.api.ndarray.INDArray> paramsMap,
          NeuralNetConfiguration conf,
          org.nd4j.linalg.api.ndarray.INDArray paramsView,
          boolean initializeParams)

Initialize the parameters

Parameters:

paramsMap - 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

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)

getGradientsFromFlattened

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. 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

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