Uses of Interface
org.deeplearning4j.nn.weights.IWeightInit
-
-
Uses of IWeightInit in org.deeplearning4j.nn.conf
Fields in org.deeplearning4j.nn.conf declared as IWeightInit Modifier and Type Field Description protected IWeightInitNeuralNetConfiguration.Builder. weightInitFnMethods in org.deeplearning4j.nn.conf with parameters of type IWeightInit Modifier and Type Method Description NeuralNetConfiguration.BuilderNeuralNetConfiguration.Builder. weightInit(IWeightInit weightInit)Weight initialization scheme to use, for initial weight values Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. -
Uses of IWeightInit in org.deeplearning4j.nn.conf.layers
Fields in org.deeplearning4j.nn.conf.layers declared as IWeightInit Modifier and Type Field Description protected IWeightInitBaseLayer.Builder. weightInitFnWeight initialization scheme to use, for initial weight valuesprotected IWeightInitBaseLayer. weightInitFnprotected IWeightInitBaseRecurrentLayer.Builder. weightInitFnRecurrentSet the weight initialization for the recurrent weights.protected IWeightInitBaseRecurrentLayer. weightInitFnRecurrentMethods in org.deeplearning4j.nn.conf.layers with parameters of type IWeightInit Modifier and Type Method Description voidEmbeddingSequenceLayer.Builder. setWeightInitFn(IWeightInit weightInit)TBaseLayer.Builder. weightInit(IWeightInit weightInit)Weight initialization scheme to use, for initial weight valuesEmbeddingLayer.BuilderEmbeddingLayer.Builder. weightInit(IWeightInit weightInit)EmbeddingSequenceLayer.BuilderEmbeddingSequenceLayer.Builder. weightInit(IWeightInit weightInit)TBaseRecurrentLayer.Builder. weightInitRecurrent(IWeightInit weightInit)Set the weight initialization for the recurrent weights. -
Uses of IWeightInit in org.deeplearning4j.nn.conf.layers.samediff
Fields in org.deeplearning4j.nn.conf.layers.samediff with type parameters of type IWeightInit Modifier and Type Field Description protected Map<String,IWeightInit>SameDiffLayer.Builder. paramWeightInitprotected Map<String,IWeightInit>SameDiffLayer. paramWeightInitMethods in org.deeplearning4j.nn.conf.layers.samediff with parameters of type IWeightInit Modifier and Type Method Description TSameDiffLayer.Builder. weightInit(@NonNull String param, @NonNull IWeightInit weightInit) -
Uses of IWeightInit in org.deeplearning4j.nn.params
Methods in org.deeplearning4j.nn.params with parameters of type IWeightInit Modifier and Type Method Description protected INDArrayDefaultParamInitializer. createWeightMatrix(long nIn, long nOut, IWeightInit weightInit, INDArray weightParamView, boolean initializeParameters)protected INDArrayElementWiseParamInitializer. createWeightMatrix(long nIn, long nOut, IWeightInit weightInit, INDArray weightParamView, boolean initializeParameters)protected INDArrayEmbeddingLayerParamInitializer. createWeightMatrix(long nIn, long nOut, IWeightInit weightInit, INDArray weightParamView, boolean initializeParameters) -
Uses of IWeightInit in org.deeplearning4j.nn.transferlearning
Fields in org.deeplearning4j.nn.transferlearning declared as IWeightInit Modifier and Type Field Description protected IWeightInitFineTuneConfiguration. weightInitFnMethods in org.deeplearning4j.nn.transferlearning with parameters of type IWeightInit Modifier and Type Method Description TransferLearning.BuilderTransferLearning.Builder. nInReplace(int layerNum, int nIn, IWeightInit scheme)Modify the architecture of a vertex layer by changing nIn of the specified layer.
Note that only the specified layer will be modified - all other layers will not be changed by this call.TransferLearning.GraphBuilderTransferLearning.GraphBuilder. nInReplace(String layerName, int nIn, IWeightInit scheme)Modify the architecture of a vertex layer by changing nIn of the specified layer.
Note that only the specified layer will be modified - all other layers will not be changed by this call.TransferLearning.BuilderTransferLearning.Builder. nOutReplace(int layerNum, int nOut, IWeightInit scheme, IWeightInit schemeNext)Modify the architecture of a layer by changing nOut Note this will also affect the layer that follows the layer specified, unless it is the output layer Can specify different weight init schemes for the specified layer and the layer that follows it.FineTuneConfiguration.BuilderFineTuneConfiguration.Builder. weightInit(IWeightInit weightInit)Weight initialization scheme to use, for initial weight values -
Uses of IWeightInit in org.deeplearning4j.nn.weights
Classes in org.deeplearning4j.nn.weights that implement IWeightInit Modifier and Type Class Description classWeightInitConstantclassWeightInitDistributionclassWeightInitIdentityclassWeightInitLecunUniformUniform U[-a,a] with a=3/sqrt(fanIn).classWeightInitNormalNormal/Gaussian distribution, with mean 0 and standard deviation 1/sqrt(fanIn).classWeightInitReluclassWeightInitReluUniformclassWeightInitSigmoidUniformclassWeightInitUniformclassWeightInitVarScalingNormalFanAvgclassWeightInitVarScalingNormalFanInclassWeightInitVarScalingNormalFanOutclassWeightInitVarScalingUniformFanAvgUniform U[-a,a] with a=3.0/((fanIn + fanOut)/2)classWeightInitVarScalingUniformFanInclassWeightInitVarScalingUniformFanOutclassWeightInitXavierclassWeightInitXavierLegacyXavier weight init in DL4J up to 0.6.0.classWeightInitXavierUniformAs per Glorot and Bengio 2010: Uniform distribution U(-s,s) with s = sqrt(6/(fanIn + fanOut))Methods in org.deeplearning4j.nn.weights that return IWeightInit Modifier and Type Method Description IWeightInitWeightInit. getWeightInitFunction()Create an instance of the weight initialization functionIWeightInitWeightInit. getWeightInitFunction(Distribution distribution)Create an instance of the weight initialization function -
Uses of IWeightInit in org.deeplearning4j.nn.weights.embeddings
Classes in org.deeplearning4j.nn.weights.embeddings that implement IWeightInit Modifier and Type Class Description classWeightInitEmbedding
-