Uses of Class
org.deeplearning4j.nn.graph.ComputationGraph

Packages that use ComputationGraph

Package	Description
org.deeplearning4j.earlystopping.saver
org.deeplearning4j.earlystopping.scorecalc
org.deeplearning4j.earlystopping.trainer
org.deeplearning4j.gradientcheck
org.deeplearning4j.nn.conf.graph
org.deeplearning4j.nn.conf.graph.rnn
org.deeplearning4j.nn.conf.layers.samediff
org.deeplearning4j.nn.graph
org.deeplearning4j.nn.graph.vertex
org.deeplearning4j.nn.graph.vertex.impl
org.deeplearning4j.nn.graph.vertex.impl.rnn
org.deeplearning4j.nn.layers.samediff
org.deeplearning4j.nn.multilayer
org.deeplearning4j.nn.transferlearning
org.deeplearning4j.nn.updater.graph
org.deeplearning4j.optimize.listeners
org.deeplearning4j.util

Uses of ComputationGraph in org.deeplearning4j.earlystopping.saver

Methods in org.deeplearning4j.earlystopping.saver that return ComputationGraph

Modifier and Type	Method and Description
ComputationGraph	LocalFileGraphSaver.getBestModel()
ComputationGraph	LocalFileGraphSaver.getLatestModel()

Methods in org.deeplearning4j.earlystopping.saver with parameters of type ComputationGraph

Modifier and Type	Method and Description
void	LocalFileGraphSaver.saveBestModel(ComputationGraph net, double score)
void	LocalFileGraphSaver.saveLatestModel(ComputationGraph net, double score)

Uses of ComputationGraph in org.deeplearning4j.earlystopping.scorecalc

Methods in org.deeplearning4j.earlystopping.scorecalc with parameters of type ComputationGraph

Modifier and Type	Method and Description
double	DataSetLossCalculatorCG.calculateScore(ComputationGraph network) Deprecated.

Uses of ComputationGraph in org.deeplearning4j.earlystopping.trainer

Constructors in org.deeplearning4j.earlystopping.trainer with parameters of type ComputationGraph

Constructor and Description
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, DataSetIterator train)
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, DataSetIterator train, EarlyStoppingListener<ComputationGraph> listener) Constructor for training using a DataSetIterator
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, MultiDataSetIterator train, EarlyStoppingListener<ComputationGraph> listener) Constructor for training using a MultiDataSetIterator

Constructor parameters in org.deeplearning4j.earlystopping.trainer with type arguments of type ComputationGraph

Constructor and Description
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, DataSetIterator train)
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, DataSetIterator train, EarlyStoppingListener<ComputationGraph> listener) Constructor for training using a DataSetIterator
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, DataSetIterator train, EarlyStoppingListener<ComputationGraph> listener) Constructor for training using a DataSetIterator
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, MultiDataSetIterator train, EarlyStoppingListener<ComputationGraph> listener) Constructor for training using a MultiDataSetIterator
EarlyStoppingGraphTrainer(EarlyStoppingConfiguration<ComputationGraph> esConfig, ComputationGraph net, MultiDataSetIterator train, EarlyStoppingListener<ComputationGraph> listener) Constructor for training using a MultiDataSetIterator

Uses of ComputationGraph in org.deeplearning4j.gradientcheck

Methods in org.deeplearning4j.gradientcheck with parameters of type ComputationGraph

Modifier and Type	Method and Description
static boolean	GradientCheckUtil.checkGradients(ComputationGraph graph, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray[] inputs, INDArray[] labels) Check backprop gradients for a ComputationGraph
static boolean	GradientCheckUtil.checkGradients(ComputationGraph graph, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray[] inputs, INDArray[] labels, INDArray[] fMask, INDArray[] lMask)
static boolean	GradientCheckUtil.checkGradients(ComputationGraph graph, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray[] inputs, INDArray[] labels, INDArray[] fMask, INDArray[] lMask, Set<String> excludeParams)
static boolean	GradientCheckUtil.checkGradients(ComputationGraph graph, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray[] inputs, INDArray[] labels, INDArray[] fMask, INDArray[] lMask, Set<String> excludeParams, Consumer<ComputationGraph> callEachIter)
static boolean	GradientCheckUtil.checkGradients(ComputationGraph graph, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray[] inputs, INDArray[] labels, INDArray[] fMask, INDArray[] lMask, Set<String> excludeParams, Integer rngSeedResetEachIter)

Method parameters in org.deeplearning4j.gradientcheck with type arguments of type ComputationGraph

Modifier and Type	Method and Description
static boolean	GradientCheckUtil.checkGradients(ComputationGraph graph, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray[] inputs, INDArray[] labels, INDArray[] fMask, INDArray[] lMask, Set<String> excludeParams, Consumer<ComputationGraph> callEachIter)

Uses of ComputationGraph in org.deeplearning4j.nn.conf.graph

Methods in org.deeplearning4j.nn.conf.graph with parameters of type ComputationGraph

Modifier and Type	Method and Description
GraphVertex	LayerVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	ScaleVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	L2Vertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	PoolHelperVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	MergeVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	FrozenVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
abstract GraphVertex	GraphVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype) Create a GraphVertex instance, for the given computation graph, given the configuration instance.
GraphVertex	PreprocessorVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	L2NormalizeVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	ElementWiseVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	ReshapeVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	UnstackVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	ShiftVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	SubsetVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	StackVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)

Uses of ComputationGraph in org.deeplearning4j.nn.conf.graph.rnn

Methods in org.deeplearning4j.nn.conf.graph.rnn with parameters of type ComputationGraph

Modifier and Type	Method and Description
LastTimeStepVertex	LastTimeStepVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
GraphVertex	DuplicateToTimeSeriesVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)
ReverseTimeSeriesVertex	ReverseTimeSeriesVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)

Uses of ComputationGraph in org.deeplearning4j.nn.conf.layers.samediff

Methods in org.deeplearning4j.nn.conf.layers.samediff with parameters of type ComputationGraph

Modifier and Type	Method and Description
GraphVertex	SameDiffVertex.instantiate(ComputationGraph graph, String name, int idx, INDArray paramsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDatatype)

Uses of ComputationGraph in org.deeplearning4j.nn.graph

Methods in org.deeplearning4j.nn.graph that return ComputationGraph

Modifier and Type	Method and Description
ComputationGraph	ComputationGraph.clone()
ComputationGraph	ComputationGraph.convertDataType(org.nd4j.linalg.api.buffer.DataType dataType) Return a copy of the network with the parameters and activations set to use the specified (floating point) data type.
static ComputationGraph	ComputationGraph.load(File f, boolean loadUpdater) Restore a ComputationGraph to a file, saved using save(File) or ModelSerializer

Uses of ComputationGraph in org.deeplearning4j.nn.graph.vertex

Fields in org.deeplearning4j.nn.graph.vertex declared as ComputationGraph

Modifier and Type	Field and Description
protected ComputationGraph	BaseGraphVertex.graph

Constructors in org.deeplearning4j.nn.graph.vertex with parameters of type ComputationGraph

Constructor and Description
BaseGraphVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, org.nd4j.linalg.api.buffer.DataType dataType)

Uses of ComputationGraph in org.deeplearning4j.nn.graph.vertex.impl

Constructors in org.deeplearning4j.nn.graph.vertex.impl with parameters of type ComputationGraph

Constructor and Description
ElementWiseVertex(ComputationGraph graph, String name, int vertexIndex, ElementWiseVertex.Op op, org.nd4j.linalg.api.buffer.DataType dataType)
ElementWiseVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, ElementWiseVertex.Op op, org.nd4j.linalg.api.buffer.DataType dataType)
InputVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] outputVertices, org.nd4j.linalg.api.buffer.DataType dataType)
L2NormalizeVertex(ComputationGraph graph, String name, int vertexIndex, int[] dimension, double eps, org.nd4j.linalg.api.buffer.DataType dataType)
L2NormalizeVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, int[] dimension, double eps, org.nd4j.linalg.api.buffer.DataType dataType)
L2Vertex(ComputationGraph graph, String name, int vertexIndex, double eps, org.nd4j.linalg.api.buffer.DataType dataType)
L2Vertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, double eps, org.nd4j.linalg.api.buffer.DataType dataType)
LayerVertex(ComputationGraph graph, String name, int vertexIndex, Layer layer, InputPreProcessor layerPreProcessor, boolean outputVertex, org.nd4j.linalg.api.buffer.DataType dataType) Create a network input vertex:
LayerVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, Layer layer, InputPreProcessor layerPreProcessor, boolean outputVertex, org.nd4j.linalg.api.buffer.DataType dataType)
MergeVertex(ComputationGraph graph, String name, int vertexIndex, org.nd4j.linalg.api.buffer.DataType dataType)
MergeVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, org.nd4j.linalg.api.buffer.DataType dataType)
PoolHelperVertex(ComputationGraph graph, String name, int vertexIndex, org.nd4j.linalg.api.buffer.DataType dataType)
PoolHelperVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, org.nd4j.linalg.api.buffer.DataType dataType)
PreprocessorVertex(ComputationGraph graph, String name, int vertexIndex, InputPreProcessor preProcessor, org.nd4j.linalg.api.buffer.DataType dataType)
PreprocessorVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, InputPreProcessor preProcessor, org.nd4j.linalg.api.buffer.DataType dataType)
ReshapeVertex(ComputationGraph graph, String name, int vertexIndex, char order, int[] newShape, int[] maskShape, org.nd4j.linalg.api.buffer.DataType dataType)
ReshapeVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, char order, int[] newShape, int[] maskShape, org.nd4j.linalg.api.buffer.DataType dataType)
ScaleVertex(ComputationGraph graph, String name, int vertexIndex, double scaleFactor, org.nd4j.linalg.api.buffer.DataType dataType)
ScaleVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, double scaleFactor, org.nd4j.linalg.api.buffer.DataType dataType)
ShiftVertex(ComputationGraph graph, String name, int vertexIndex, double shiftFactor, org.nd4j.linalg.api.buffer.DataType dataType)
ShiftVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, double shiftFactor, org.nd4j.linalg.api.buffer.DataType dataType)
StackVertex(ComputationGraph graph, String name, int vertexIndex, org.nd4j.linalg.api.buffer.DataType dataType)
StackVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, org.nd4j.linalg.api.buffer.DataType dataType)
SubsetVertex(ComputationGraph graph, String name, int vertexIndex, int from, int to, org.nd4j.linalg.api.buffer.DataType dataType)
SubsetVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, int from, int to, org.nd4j.linalg.api.buffer.DataType dataType)
UnstackVertex(ComputationGraph graph, String name, int vertexIndex, int from, int stackSize, org.nd4j.linalg.api.buffer.DataType dataType)
UnstackVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, int from, int stackSize, org.nd4j.linalg.api.buffer.DataType dataType)

Uses of ComputationGraph in org.deeplearning4j.nn.graph.vertex.impl.rnn

Constructors in org.deeplearning4j.nn.graph.vertex.impl.rnn with parameters of type ComputationGraph

Constructor and Description
DuplicateToTimeSeriesVertex(ComputationGraph graph, String name, int vertexIndex, String inputVertexName, org.nd4j.linalg.api.buffer.DataType dataType)
DuplicateToTimeSeriesVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, String inputName, org.nd4j.linalg.api.buffer.DataType dataType)
LastTimeStepVertex(ComputationGraph graph, String name, int vertexIndex, String inputName, org.nd4j.linalg.api.buffer.DataType dataType)
LastTimeStepVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, String inputName, org.nd4j.linalg.api.buffer.DataType dataType)
ReverseTimeSeriesVertex(ComputationGraph graph, String name, int vertexIndex, String inputName, org.nd4j.linalg.api.buffer.DataType dataType)

Uses of ComputationGraph in org.deeplearning4j.nn.layers.samediff

Constructors in org.deeplearning4j.nn.layers.samediff with parameters of type ComputationGraph

Constructor and Description
SameDiffGraphVertex(SameDiffVertex config, ComputationGraph graph, String name, int vertexIndex, INDArray paramsView, boolean initParams, org.nd4j.linalg.api.buffer.DataType dataType)

Uses of ComputationGraph in org.deeplearning4j.nn.multilayer

Methods in org.deeplearning4j.nn.multilayer that return ComputationGraph

Modifier and Type	Method and Description
ComputationGraph	MultiLayerNetwork.toComputationGraph() Convert this MultiLayerNetwork to a ComputationGraph

Uses of ComputationGraph in org.deeplearning4j.nn.transferlearning

Methods in org.deeplearning4j.nn.transferlearning that return ComputationGraph

Modifier and Type	Method and Description
ComputationGraph	TransferLearning.GraphBuilder.build() Returns a computation graph build to specifications.
ComputationGraph	TransferLearningHelper.unfrozenGraph() Returns the unfrozen subset of the original computation graph as a computation graph Note that with each call to featurizedFit the parameters to the original computation graph are also updated

Constructors in org.deeplearning4j.nn.transferlearning with parameters of type ComputationGraph

Constructor and Description
GraphBuilder(ComputationGraph origGraph) Computation Graph to tweak for transfer learning
TransferLearningHelper(ComputationGraph orig) Expects a computation graph where some vertices are frozen
TransferLearningHelper(ComputationGraph orig, String... frozenOutputAt) Will modify the given comp graph (in place!) to freeze vertices from input to the vertex specified.

Uses of ComputationGraph in org.deeplearning4j.nn.updater.graph

Constructors in org.deeplearning4j.nn.updater.graph with parameters of type ComputationGraph

Constructor and Description
ComputationGraphUpdater(ComputationGraph graph)
ComputationGraphUpdater(ComputationGraph graph, INDArray updaterState)

Uses of ComputationGraph in org.deeplearning4j.optimize.listeners

Methods in org.deeplearning4j.optimize.listeners that return ComputationGraph

Modifier and Type	Method and Description
ComputationGraph	CheckpointListener.loadCheckpointCG(Checkpoint checkpoint) Load a ComputationGraph for the given checkpoint
static ComputationGraph	CheckpointListener.loadCheckpointCG(File rootDir, Checkpoint checkpoint) Load a ComputationGraph for the given checkpoint from the specified root direcotry
static ComputationGraph	CheckpointListener.loadCheckpointCG(File rootDir, int checkpointNum) Load a ComputationGraph for the given checkpoint that resides in the specified root directory
ComputationGraph	CheckpointListener.loadCheckpointCG(int checkpointNum) Load a ComputationGraph for the given checkpoint
static ComputationGraph	CheckpointListener.loadLastCheckpointCG(File rootDir) Load the last (most recent) checkpoint from the specified root directory

Uses of ComputationGraph in org.deeplearning4j.util

Methods in org.deeplearning4j.util that return ComputationGraph

Modifier and Type	Method and Description
static ComputationGraph	ModelSerializer.restoreComputationGraph(File file) Load a computation graph from a file
static ComputationGraph	ModelSerializer.restoreComputationGraph(File file, boolean loadUpdater) Load a computation graph from a file
static ComputationGraph	ModelSerializer.restoreComputationGraph(InputStream is) Load a computation graph from a InputStream
static ComputationGraph	ModelSerializer.restoreComputationGraph(InputStream is, boolean loadUpdater) Load a computation graph from a InputStream
static ComputationGraph	ModelSerializer.restoreComputationGraph(String path) Load a computation graph from a file
static ComputationGraph	ModelSerializer.restoreComputationGraph(String path, boolean loadUpdater) Load a computation graph from a file
static ComputationGraph	NetworkUtils.toComputationGraph(MultiLayerNetwork net) Convert a MultiLayerNetwork to a ComputationGraph

Methods in org.deeplearning4j.util that return types with arguments of type ComputationGraph

Modifier and Type	Method and Description
static Pair<ComputationGraph,Normalizer>	ModelSerializer.restoreComputationGraphAndNormalizer(File file, boolean loadUpdater) Restore a ComputationGraph and Normalizer (if present - null if not) from a File
static Pair<ComputationGraph,Normalizer>	ModelSerializer.restoreComputationGraphAndNormalizer(InputStream is, boolean loadUpdater) Restore a ComputationGraph and Normalizer (if present - null if not) from the InputStream.

Methods in org.deeplearning4j.util with parameters of type ComputationGraph

Modifier and Type	Method and Description
static Double	NetworkUtils.getLearningRate(ComputationGraph net, String layerName) Get the current learning rate, for the specified layer, from the network.
static void	NetworkUtils.setLearningRate(ComputationGraph net, double newLr) Set the learning rate for all layers in the network to the specified value.
static void	NetworkUtils.setLearningRate(ComputationGraph net, ISchedule newLrSchedule) Set the learning rate schedule for all layers in the network to the specified schedule.
static void	NetworkUtils.setLearningRate(ComputationGraph net, String layerName, double newLr) Set the learning rate for a single layer in the network to the specified value.
static void	NetworkUtils.setLearningRate(ComputationGraph net, String layerName, ISchedule lrSchedule) Set the learning rate schedule for a single layer in the network to the specified value. Note also that NetworkUtils.setLearningRate(ComputationGraph, ISchedule) should also be used in preference, when all layers need to be set to a new LR schedule. This schedule will replace any/all existing schedules, and also any fixed learning rate values. Note also that the iteration/epoch counts will not be reset.