Index

A B C D E F G H I K L M N O P Q R S T U V W X Z
All Classes and Interfaces|All Packages

G

GAT - Class in nodeClassification

GAT() - Constructor for class nodeClassification.GAT

Gather - Class in mklab.JGNN.nn.operations

Implements a NNOperation that performs the equivalent of TensorFlow's gather operation.

Gather() - Constructor for class mklab.JGNN.nn.operations.Gather

GCN - Class in nodeClassification

Demonstrates classification with the GCN architecture.

GCN() - Constructor for class nodeClassification.GCN

GCNII - Class in nodeClassification

GCNII() - Constructor for class nodeClassification.GCNII

get() - Method in class mklab.JGNN.nn.inputs.Parameter

Gets sets the parameter's value tensor

get(int) - Method in class mklab.JGNN.core.tensor.DenseTensor

get(int) - Method in class mklab.JGNN.core.tensor.VectorizedTensor

get(long) - Method in class mklab.JGNN.adhoc.IdConverter

Retrieves the object corresponding to a given identifier.

get(long) - Method in class mklab.JGNN.core.empty.EmptyMatrix

get(long) - Method in class mklab.JGNN.core.empty.EmptyTensor

get(long) - Method in class mklab.JGNN.core.matrix.AccessCol

get(long) - Method in class mklab.JGNN.core.matrix.AccessRow

get(long) - Method in class mklab.JGNN.core.matrix.ColumnRepetition

get(long) - Method in class mklab.JGNN.core.matrix.DenseMatrix

get(long) - Method in class mklab.JGNN.core.matrix.Diagonal

get(long) - Method in class mklab.JGNN.core.matrix.RepeatMatrix

get(long) - Method in class mklab.JGNN.core.matrix.RowRepetition

get(long) - Method in class mklab.JGNN.core.matrix.SparseMatrix

get(long) - Method in class mklab.JGNN.core.matrix.SparseSymmetric

Deprecated.

get(long) - Method in class mklab.JGNN.core.matrix.TransposedMatrix

get(long) - Method in class mklab.JGNN.core.matrix.VectorizedMatrix

get(long) - Method in class mklab.JGNN.core.matrix.WrapCols

get(long) - Method in class mklab.JGNN.core.matrix.WrapRows

get(long) - Method in class mklab.JGNN.core.tensor.AccessSubtensor

get(long) - Method in class mklab.JGNN.core.tensor.DenseTensor

get(long) - Method in class mklab.JGNN.core.Tensor

Retrieves the value of a tensor element at a given position.

get(long) - Method in class mklab.JGNN.core.tensor.RepeatTensor

get(long) - Method in class mklab.JGNN.core.tensor.SparseTensor

get(long) - Method in class mklab.JGNN.core.tensor.VectorizedTensor

get(long, long) - Method in class mklab.JGNN.core.Matrix

Retrieves the value stored at a matrix element.

get(String) - Method in class mklab.JGNN.adhoc.ModelBuilder

Retrieves the NNOperation registered with the provided name, for example to investigates its value.

getBatchData(int, int) - Method in class mklab.JGNN.adhoc.ModelTraining

Returns a list BatchData instance to be used for a specific batch and training epoch.

getBatchData(int, int) - Method in class mklab.JGNN.adhoc.train.AGFTraining

getBatchData(int, int) - Method in class mklab.JGNN.adhoc.train.SampleClassification

getColName() - Method in class mklab.JGNN.core.Matrix

getCols() - Method in class mklab.JGNN.core.Matrix

Retrieves the number of columns of a matrix.

getColumn() - Method in class mklab.JGNN.core.matrix.ColumnRepetition

Retrieves the wrapped column tensor.

getConfig(String) - Method in class mklab.JGNN.adhoc.ModelBuilder

Retrieves a configuration hyperparameter's value.

getConfigOrDefault(String, double) - Method in class mklab.JGNN.adhoc.ModelBuilder

Retrieves a configuration hyperparameter's value.

getCurrentThreadId() - Static method in class mklab.JGNN.core.ThreadPool

Retrieves a unique integer indicating the currently running thread.

getDepthLastOperations() - Method in class mklab.JGNN.nn.Model

Retrieves a list of operations by traversing the model's execution graph with the depth-first algorithm in the inverse edge order (starting from the outputs).

getDescription() - Method in class mklab.JGNN.nn.NNOperation

getDeviation() - Method in interface mklab.JGNN.core.Distribution

Retrieves the distribution's standard deviation.

getDeviation() - Method in class mklab.JGNN.core.distribution.Normal

getDeviation() - Method in class mklab.JGNN.core.distribution.Uniform

getDimensionName() - Method in class mklab.JGNN.core.Tensor

getDimensionSize(String) - Method in class mklab.JGNN.core.Matrix

Retrieves the value of the dimension with the given name.

getDistribution(long, long, double) - Method in class mklab.JGNN.nn.initializers.KaimingNormal

getDistribution(long, long, double) - Method in class mklab.JGNN.nn.initializers.KaimingUniform

getDistribution(long, long, double) - Method in class mklab.JGNN.nn.initializers.VariancePreservingInitializer

getDistribution(long, long, double) - Method in class mklab.JGNN.nn.initializers.XavierNormal

getDistribution(long, long, double) - Method in class mklab.JGNN.nn.initializers.XavierUniform

getExecutionGraphDot() - Method in class mklab.JGNN.adhoc.ModelBuilder

Exports the builded model's execution graph into a .dot format representation.

getId(Object) - Method in class mklab.JGNN.adhoc.IdConverter

Retrieves an identifier.

getInputs() - Method in class mklab.JGNN.adhoc.BatchData

getInputs() - Method in class mklab.JGNN.nn.Model

Retrieves a list of model inputs.

getInputs() - Method in class mklab.JGNN.nn.NNOperation

Retrieves a list of input operations within a model's execution graph.

getInstance() - Static method in class mklab.JGNN.core.ThreadPool

Retrieves the singleton ThreadPool instance used by JGNN.

getKey() - Method in class mklab.JGNN.core.util.FastEntry

getLastTapeError() - Method in class mklab.JGNN.nn.NNOperation

getMean() - Method in interface mklab.JGNN.core.Distribution

Retrieves the distribution's mean.

getMean() - Method in class mklab.JGNN.core.distribution.Normal

getMean() - Method in class mklab.JGNN.core.distribution.Uniform

getMemory() - Method in class mklab.JGNN.nn.operations.LSTM.LSTMState

getModel() - Method in class mklab.JGNN.adhoc.ModelBuilder

Retrieves the model currently built by the builder.

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.activations.Exp

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.activations.LRelu

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.activations.NExp

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.activations.PRelu

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.activations.Relu

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.activations.Sigmoid

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.activations.Tanh

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.NNOperation

Retrieves the degree of non-linearity of the operation to be used by VariancePreservingInitializer.

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.operations.MatMul

getNonLinearity(int, double, double) - Method in class mklab.JGNN.nn.operations.Multiply

getNonZeroElements() - Method in class mklab.JGNN.core.Tensor

Retrieves an iterable that wraps Tensor.traverseNonZeroElements().

getNonZeroEntries() - Method in class mklab.JGNN.core.empty.EmptyMatrix

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.ColumnRepetition

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.DenseMatrix

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.Diagonal

getNonZeroEntries() - Method in class mklab.JGNN.core.Matrix

Retrieves an iterable that traverses (row, col) entry pairs of non zero entries.

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.RepeatMatrix

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.RowRepetition

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.SparseMatrix

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.SparseSymmetric

Deprecated.

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.TransposedMatrix

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.VectorizedMatrix

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.WrapCols

getNonZeroEntries() - Method in class mklab.JGNN.core.matrix.WrapRows

getOptimizer() - Method in class mklab.JGNN.nn.operations.LSTM

getOrCreateId(Object) - Method in class mklab.JGNN.adhoc.IdConverter

Retrieves an identifier for a given object, creating one if none exists.

getOutput() - Method in class mklab.JGNN.nn.operations.LSTM.LSTMState

getOutputs() - Method in class mklab.JGNN.adhoc.BatchData

getOutputs() - Method in class mklab.JGNN.nn.Model

Retrieves a list of model outputs.

getOutputs() - Method in class mklab.JGNN.nn.NNOperation

Retrieves a list of output operations within a model's execution graph.

getParameters() - Method in class mklab.JGNN.nn.Model

Retrieves a list of all parameters eventually leading to the model's outputs.

getPrediction() - Method in class mklab.JGNN.nn.NNOperation

getRowName() - Method in class mklab.JGNN.core.Matrix

getRows() - Method in class mklab.JGNN.core.Matrix

Retrieves the number of rows of a matrix.

getSimpleDescription() - Method in class mklab.JGNN.nn.NNOperation

Provides a simple description to show when drawing .dot format diagrams.

getSimpleDescription() - Method in class mklab.JGNN.nn.operations.Reshape

getSlice() - Method in class mklab.JGNN.adhoc.IdConverter

Returns a slice of all registered identifiers.

getThreadId() - Method in class mklab.JGNN.nn.NNOperation.ThreadData

getUnusedId() - Method in class mklab.JGNN.core.ThreadPool

getValidationData(int) - Method in class mklab.JGNN.adhoc.ModelTraining

Returns a BatchData instance to be used for validation at a given training epoch.

getValidationData(int) - Method in class mklab.JGNN.adhoc.train.AGFTraining

getValidationData(int) - Method in class mklab.JGNN.adhoc.train.SampleClassification

getValue() - Method in class mklab.JGNN.core.util.FastEntry

GradientDescent - Class in mklab.JGNN.nn.optimizers

Implements a gradient descent Optimizer.

GradientDescent() - Constructor for class mklab.JGNN.nn.optimizers.GradientDescent

GradientDescent(double) - Constructor for class mklab.JGNN.nn.optimizers.GradientDescent

Initializes a GradientDescent optimizer with fixed learning rate.

GradientDescent(double, double) - Constructor for class mklab.JGNN.nn.optimizers.GradientDescent

Initializes a GradientDescent optimizer with degrading learning rate.

graph() - Method in class mklab.JGNN.adhoc.Dataset

Retrieves the dataset's graph.

graphClassification - package graphClassification

graphs - Variable in class graphClassification.TrajectoryData

A B C D E F G H I K L M N O P Q R S T U V W X Z
All Classes and Interfaces|All Packages