ComputationGraph (deeplearning4j-nn 1.0.0-beta7 API)

java.lang.Object
- org.deeplearning4j.nn.graph.ComputationGraph

All Implemented Interfaces:

Serializable, Model, NeuralNetwork
```
public class ComputationGraph
extends Object
implements Serializable, Model, NeuralNetwork
```
A ComputationGraph network is a neural network with arbitrary (directed acyclic graph) connection structure. A ComputationGraph may also have an arbitrary number of inputs and outputs.

Author:

Alex Black

See Also:

Serialized Form

Field Summary

Fields
Modifier and Type	Field and Description
`protected boolean`	`clearTbpttState`
`protected ComputationGraphConfiguration`	`configuration`
`protected INDArray`	`flattenedGradients`
`protected INDArray`	`flattenedParams`
`protected Gradient`	`gradient`
`protected GraphIndices`	`graphIndices` Topological sort and vertex index/name + name/index mapping
`protected Map<String,org.bytedeco.javacpp.Pointer>`	`helperWorkspaces`
`protected boolean`	`initCalled`
`protected ThreadLocal<Long>`	`lastEtlTime`
`protected Layer[]`	`layers` A list of layers.
`protected double`	`score`
`protected Solver`	`solver`
`protected int[]`	`topologicalOrder` Indexes of graph vertices, in topological order.
`protected GraphVertex[]`	`vertices` All GraphVertex objects in the network.
`protected Map<String,GraphVertex>`	`verticesMap` Map of vertices by name
`protected static String`	`WS_ALL_LAYERS_ACT` Workspace for storing all layers' activations - used only to store activations (layer inputs) as part of backprop Not used for inference
`protected static WorkspaceConfiguration`	`WS_ALL_LAYERS_ACT_CONFIG`
`protected WorkspaceConfiguration`	`WS_LAYER_ACT_X_CONFIG`
`protected static String`	`WS_LAYER_WORKING_MEM` Workspace for working memory for a single layer: forward pass and backward pass Note that this is opened/closed once per op (activate/backpropGradient call)
`protected WorkspaceConfiguration`	`WS_LAYER_WORKING_MEM_CONFIG`
`protected static String`	`WS_OUTPUT_MEM` Workspace for output methods that use OutputAdapter
`protected static String`	`WS_RNN_LOOP_WORKING_MEM` Workspace for working memory in RNNs - opened and closed once per RNN time step
`protected static WorkspaceConfiguration`	`WS_RNN_LOOP_WORKING_MEM_CONFIG`

Constructor Summary

Constructors
Constructor and Description

ComputationGraph(ComputationGraphConfiguration configuration)

Constructors
Constructor and Description
`ComputationGraph(ComputationGraphConfiguration configuration)`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`void`	`addListeners(TrainingListener... listeners)` This method ADDS additional TrainingListener to existing listeners
`void`	`applyConstraints(int iteration, int epoch)` Apply any constraints to the model
`Gradient`	`backpropGradient(INDArray... epsilons)` Calculate the gradient of the network with respect to some external errors.
`int`	`batchSize()` The current inputs batch size
`protected void`	`calcBackpropGradients(boolean clearLayers, boolean truncatedBPTT, INDArray... externalEpsilons)` Do backprop (gradient calculation)
`double`	`calcRegularizationScore(boolean backpropParamsOnly)`
`GraphIndices`	`calculateIndices()` Calculate the indices needed for the network: (a) topological sort order (b) Map: vertex index -> vertex name (c) Map: vertex name -> vertex index
`void`	`clear()` Clear input
`void`	`clearLayerMaskArrays()` Remove the mask arrays from all layers. See `setLayerMaskArrays(INDArray[], INDArray[])` for details on mask arrays.
`void`	`clearLayersStates()` This method just makes sure there's no state preserved within layers
`ComputationGraph`	`clone()`
`void`	`close()` Close the network and deallocate all native memory, including: parameters, gradients, updater memory and workspaces Note that the network should not be used again for any purpose after it has been closed
`void`	`computeGradientAndScore()`
`void`	`computeGradientAndScore(LayerWorkspaceMgr workspaceMgr)` Update the score
`NeuralNetConfiguration`	`conf()` The configuration for the neural network
`ComputationGraph`	`convertDataType(@NonNull DataType dataType)` Return a copy of the network with the parameters and activations set to use the specified (floating point) data type.
`<T extends IEvaluation> T[]`	`doEvaluation(DataSetIterator iterator, T... evaluations)` Perform evaluation on the given data (DataSetIterator) with the given `IEvaluation` instance
`<T extends IEvaluation> T[]`	`doEvaluation(MultiDataSetIterator iterator, T... evaluations)` Perform evaluation on the given data (MultiDataSetIterator) with the given `IEvaluation` instance
`protected void`	`doTruncatedBPTT(INDArray[] inputs, INDArray[] labels, INDArray[] featureMasks, INDArray[] labelMasks, LayerWorkspaceMgr workspaceMgr)` Fit the network using truncated BPTT
`boolean`	`equals(Object obj)` Indicates whether some other object is "equal to" this one.
`<T extends Evaluation> T`	`evaluate(DataSetIterator iterator)` Evaluate the network (classification performance - single output ComputationGraphs only)
`<T extends Evaluation> T`	`evaluate(DataSetIterator iterator, List<String> labelsList)` Evaluate the network on the provided data set (single output ComputationGraphs only).
`<T extends Evaluation> T`	`evaluate(DataSetIterator iterator, List<String> labelsList, int topN)` Evaluate the network (for classification) on the provided data set, with top N accuracy in addition to standard accuracy.
`<T extends IEvaluation> Map<Integer,T[]>`	`evaluate(DataSetIterator iterator, Map<Integer,T[]> evaluations)` Perform evaluation for networks with multiple outputs.
`<T extends Evaluation> T`	`evaluate(MultiDataSetIterator iterator)` Evaluate the network (classification performance - single output ComputationGraphs only)
`<T extends Evaluation> T`	`evaluate(MultiDataSetIterator iterator, List<String> labelsList)` Evaluate the network on the provided data set (single output ComputationGraphs only).
`<T extends Evaluation> T`	`evaluate(MultiDataSetIterator iterator, List<String> labelsList, int topN)` Evaluate the network (for classification) on the provided data set, with top N accuracy in addition to standard accuracy.
`<T extends IEvaluation> Map<Integer,T[]>`	`evaluate(MultiDataSetIterator iterator, Map<Integer,T[]> evaluations)` Perform evaluation for networks with multiple outputs.
`<T extends RegressionEvaluation> T`	`evaluateRegression(DataSetIterator iterator)` Evaluate the (single output layer only) network for regression performance
`<T extends RegressionEvaluation> T`	`evaluateRegression(DataSetIterator iterator, List<String> columnNames)` Evaluate the (single output layer only) network for regression performance
`<T extends RegressionEvaluation> T`	`evaluateRegression(MultiDataSetIterator iterator)` Evaluate the (single output layer only) network for regression performance
`<T extends RegressionEvaluation> T`	`evaluateRegression(MultiDataSetIterator iterator, List<String> columnNames)` Evaluate the (single output layer only) network for regression performance
`<T extends ROC> T`	`evaluateROC(DataSetIterator iterator)` Deprecated. To be removed - use `evaluateROC(DataSetIterator, int)` to enforce selection of appropriate ROC/threshold configuration
`<T extends ROC> T`	`evaluateROC(DataSetIterator iterator, int rocThresholdSteps)` Evaluate the network (must be a binary classifier) on the specified data, using the `ROC` class
`<T extends ROC> T`	`evaluateROC(MultiDataSetIterator iterator)` Deprecated. To be removed - use `evaluateROC(DataSetIterator, int)` to enforce selection of appropriate ROC/threshold configuration
`<T extends ROC> T`	`evaluateROC(MultiDataSetIterator iterator, int rocThresholdSteps)` Evaluate the network (must be a binary classifier) on the specified data, using the `ROC` class
`<T extends ROCMultiClass> T`	`evaluateROCMultiClass(DataSetIterator iterator)` Deprecated. To be removed - use `evaluateROCMultiClass(DataSetIterator, int)` to enforce selection of appropriate ROC/threshold configuration
`<T extends ROCMultiClass> T`	`evaluateROCMultiClass(DataSetIterator iterator, int rocThresholdSteps)` Evaluate the network on the specified data, using the `ROCMultiClass` class
`<T extends ROCMultiClass> T`	`evaluateROCMultiClass(MultiDataSetIterator iterator, int rocThresholdSteps)` Evaluate the network on the specified data, using the `ROCMultiClass` class
`Map<String,INDArray>`	`feedForward()` Conduct forward pass using the stored inputs, at test time
`Map<String,INDArray>`	`feedForward(boolean train)` Conduct forward pass using the stored inputs
`Map<String,INDArray>`	`feedForward(boolean train, boolean excludeOutputLayers, boolean includeNonLayerVertexActivations)`
`Map<String,INDArray>`	`feedForward(boolean train, int layerTillIndex)` Conduct forward pass using the stored inputs
`Map<String,INDArray>`	`feedForward(INDArray[] input, boolean train)` Conduct forward pass using an array of inputs
`Map<String,INDArray>`	`feedForward(INDArray[] input, boolean train, boolean clearInputs)` Conduct forward pass using an array of inputs.
`Map<String,INDArray>`	`feedForward(INDArray[] input, int layerTillIndex, boolean train)` Conduct forward pass using an array of inputs
`Map<String,INDArray>`	`feedForward(INDArray[] input, int layerTillIndex, boolean train, boolean clearInputs)` Conduct forward pass using an array of inputs.
`Map<String,INDArray>`	`feedForward(INDArray input, boolean train)` Conduct forward pass using a single input array.
`Map<String,INDArray>`	`feedForward(INDArray input, int layerTillIndex, boolean train)` Conduct forward pass using a single input array.
`protected Map<String,INDArray>`	`ffToLayerActivationsDetached(boolean train, @NonNull FwdPassType fwdPassType, boolean storeLastForTBPTT, int layerIndex, int[] excludeIdxs, @NonNull INDArray[] features, INDArray[] fMask, INDArray[] lMask, boolean clearLayers)` Feed-forward through the network - returning all array activations detached from any workspace.
`protected Map<String,INDArray>`	`ffToLayerActivationsInWS(boolean train, int layerIndex, int[] excludeIdxs, FwdPassType fwdPassType, boolean storeLastForTBPTT, INDArray[] input, INDArray[] fMask, INDArray[] lMask, boolean clearInputs)` Feed-forward through the network - if workspaces are used, all returned activations will be present in workspace WS_ALL_LAYERS_ACT. Note: if using workspaces for training, requires that WS_ALL_LAYERS_ACT is open externally.
`void`	`fit()` All models have a fit method
`void`	`fit(DataSet dataSet)` Fit the ComputationGraph using a DataSet.
`void`	`fit(@NonNull DataSetIterator iterator)` Fit the ComputationGraph using a DataSetIterator. Note that this method can only be used with ComputationGraphs with 1 input and 1 output Method doesn't do layerwise pretraining. For pretraining use method pretrain..
`void`	`fit(@NonNull DataSetIterator iterator, int numEpochs)` Perform minibatch training on all minibatches in the DataSetIterator, for the specified number of epochs.
`void`	`fit(INDArray[] inputs, INDArray[] labels)` Fit the ComputationGraph given arrays of inputs and labels.
`void`	`fit(INDArray[] inputs, INDArray[] labels, INDArray[] featureMaskArrays, INDArray[] labelMaskArrays)` Fit the ComputationGraph using the specified inputs and labels (and mask arrays)
`void`	`fit(INDArray data, LayerWorkspaceMgr workspaceMgr)` Fit the model to the given data
`void`	`fit(MultiDataSet multiDataSet)` Fit the ComputationGraph using a MultiDataSet
`void`	`fit(MultiDataSetIterator multi)` Fit the ComputationGraph using a MultiDataSetIterator Method doesn't do layerwise pretraining. For pretraining use method pretrain..
`void`	`fit(@NonNull MultiDataSetIterator iterator, int numEpochs)` Perform minibatch training on all minibatches in the MultiDataSetIterator, for the specified number of epochs.
`ComputationGraphConfiguration`	`getConfiguration()` This method returns configuration of this ComputationGraph
`int`	`getEpochCount()` Returns the number of epochs that the ComputationGraph has done.
`INDArray`	`getGradientsViewArray()`
`INDArray`	`getInput(int inputNum)` Get the previously set input for the ComputationGraph
`INDArray[]`	`getInputMaskArrays()` Get the previously set feature/input mask arrays for the ComputationGraph
`INDArray[]`	`getInputs()` Get the previously set inputs for the ComputationGraph
`int`	`getIterationCount()` Returns the number of iterations (parameter updates) that the ComputationGraph has done
`INDArray[]`	`getLabelMaskArrays()` Get the previously set label/output mask arrays for the ComputationGraph
`long`	`getLastEtlTime()` This method returns ETL time field value
`Layer`	`getLayer(int idx)` Get the layer by the number of that layer, in range 0 to getNumLayers()-1 NOTE: This is different from the internal GraphVertex index for the layer
`Layer`	`getLayer(String name)` Get a given layer by name.
`Layer[]`	`getLayers()` Get all layers in the ComputationGraph
`Double`	`getLearningRate(String layerName)` Get the current learning rate, for the specified layer, from the network.
`Collection<TrainingListener>`	`getListeners()` Get the trainingListeners for the ComputationGraph
`int`	`getNumInputArrays()` The number of inputs to this network
`int`	`getNumLayers()` Returns the number of layers in the ComputationGraph
`int`	`getNumOutputArrays()` The number of output (arrays) for this network
`ConvexOptimizer`	`getOptimizer()` Returns this models optimizer
`Layer`	`getOutputLayer(int outputLayerIdx)` Get the specified output layer, by index.
`protected int[]`	`getOutputLayerIndices()`
`INDArray`	`getParam(String paramName)` Get the parameter
`ComputationGraphUpdater`	`getUpdater()` Get the ComputationGraphUpdater for the network.
`ComputationGraphUpdater`	`getUpdater(boolean initializeIfAbsent)` Get the ComputationGraphUpdater for this network
`GraphVertex`	`getVertex(String name)` Return a given GraphVertex by name, or null if no vertex with that name exists
`GraphVertex[]`	`getVertices()` Returns an array of all GraphVertex objects.
`Gradient`	`gradient()` Get the gradient.
`Pair<Gradient,Double>`	`gradientAndScore()` Get the gradient and score
`void`	`incrementEpochCount()` Increment the epoch count (in the underlying `ComputationGraphConfiguration` by 1).
`void`	`init()` Initialize the ComputationGraph network
`void`	`init(INDArray parameters, boolean cloneParametersArray)` Initialize the ComputationGraph, optionally with an existing parameters array.
`void`	`initGradientsView()` This method: initializes the flattened gradients array (used in backprop) and sets the appropriate subset in all layers.
`INDArray`	`input()` The input/feature matrix for the model
`long`	`layerInputSize(int layer)` Return the input size (number of inputs) for the specified layer. Note that the meaning of the "input size" can depend on the type of layer.
`long`	`layerInputSize(String layerName)` Return the input size (number of inputs) for the specified layer. Note that the meaning of the "input size" can depend on the type of layer.
`long`	`layerSize(int layer)` Return the layer size (number of units) for the specified layer.
`long`	`layerSize(String layerName)` Return the layer size (number of units) for the specified layer. Note that the meaning of the "layer size" can depend on the type of layer.
`static ComputationGraph`	`load(File f, boolean loadUpdater)` Restore a ComputationGraph to a file, saved using `save(File)` or `ModelSerializer`
`String`	`memoryInfo(int minibatch, InputType... inputTypes)` Generate information regarding memory use for the network, for the given input types and minibatch size.
`long`	`numParams()` the number of parameters for the model
`long`	`numParams(boolean backwards)` the number of parameters for the model
`INDArray[]`	`output(boolean train, boolean clearInputs, INDArray... input)` An output method for the network, with optional clearing of the layer inputs. Note: most users should use `output(boolean, INDArray...)` or similar methods, unless they are doing non-standard operations (like providing the input arrays externally)
`INDArray[]`	`output(boolean train, INDArray... input)` Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
`INDArray[]`	`output(boolean train, @NonNull INDArray[] input, INDArray[] inputMasks)` Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
`INDArray[]`	`output(boolean train, @NonNull INDArray[] input, INDArray[] inputMasks, INDArray[] labelMasks)` Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
`INDArray[]`	`output(boolean train, @NonNull INDArray[] input, INDArray[] inputMasks, INDArray[] labelMasks, MemoryWorkspace outputWorkspace)` Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only. If no memory workspace is provided, the output will be detached (not in any workspace). If a memory workspace is provided, the output activation array (i.e., the INDArray returned by this method) will be placed in the specified workspace.
`INDArray[]`	`output(boolean train, MemoryWorkspace outputWorkspace, INDArray... input)` Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only. If no memory workspace is provided, the output will be detached (not in any workspace). If a memory workspace is provided, the output activation array (i.e., the INDArray returned by this method) will be placed in the specified workspace.
`INDArray[]`	`output(DataSetIterator iterator)` Generate the output for all examples/batches in the input iterator, and concatenate them into a single array per network output
`INDArray[]`	`output(INDArray... input)` Return an array of network outputs (predictions) at test time, given the specified network inputs Network outputs are for output layers only.
`<T> T`	`output(@NonNull INDArray[] inputs, INDArray[] inputMasks, INDArray[] labelMasks, @NonNull OutputAdapter<T> outputAdapter)` This method uses provided OutputAdapter to return custom object built from INDArray PLEASE NOTE: This method uses dedicated Workspace for output generation to avoid redundant allocations
`INDArray[]`	`output(List<String> layers, boolean train, INDArray[] features, INDArray[] featureMasks)` Get the activations for the specific layers only
`INDArray[]`	`output(MultiDataSetIterator iterator)` Generate the output for all examples/batches in the input iterator, and concatenate them into a single array per network output
`protected INDArray[]`	`outputOfLayersDetached(boolean train, @NonNull FwdPassType fwdPassType, @NonNull int[] layerIndexes, @NonNull INDArray[] features, INDArray[] fMask, INDArray[] lMasks, boolean clearLayerInputs, boolean detachedInputs, MemoryWorkspace outputWorkspace)` Provide the output of the specified layers, detached from any workspace.
`INDArray`	`outputSingle(boolean train, boolean clearInputs, INDArray... input)` Identical to `outputSingle(boolean, boolean, INDArray...)` but has the option of not clearing the input arrays (useful when later backpropagating external errors).
`INDArray`	`outputSingle(boolean train, INDArray... input)` A convenience method that returns a single INDArray, instead of an INDArray[].
`INDArray`	`outputSingle(DataSetIterator iterator)` Generate the output for all examples/batches in the input iterator, and concatenate them into a single array.
`INDArray`	`outputSingle(INDArray... input)` A convenience method that returns a single INDArray, instead of an INDArray[].
`INDArray`	`outputSingle(MultiDataSetIterator iterator)` Generate the output for all examples/batches in the input iterator, and concatenate them into a single array.
`INDArray`	`params()` Parameters of the model (if any)
`INDArray`	`params(boolean backwardOnly)` Deprecated. To be removed. Use `params()`
`Map<String,INDArray>`	`paramTable()` The param table
`Map<String,INDArray>`	`paramTable(boolean backpropParamsOnly)` Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters
`void`	`pretrain(DataSetIterator iter)` Perform layerwise pretraining for one epoch - see `pretrain(DataSetIterator, int)`
`void`	`pretrain(DataSetIterator iter, int numEpochs)` Pretrain network with a single input and single output.
`void`	`pretrain(MultiDataSetIterator iter)` Pretrain network with multiple inputs and/or outputs
`void`	`pretrain(MultiDataSetIterator iter, int numEpochs)` Pretrain network with multiple inputs and/or outputs This method performs layerwise pretraining on all pre-trainable layers in the network (VAEs, Autoencoders, etc), for the specified number of epochs each.
`void`	`pretrainLayer(String layerName, DataSetIterator dataSetIterator)` Pretrain a specified layer with the given DataSetIterator
`void`	`pretrainLayer(String layerName, MultiDataSetIterator iter)` Pretrain a specified layer with the given MultiDataSetIterator
`Map<String,INDArray>`	`rnnActivateUsingStoredState(INDArray[] inputs, boolean training, boolean storeLastForTBPTT)` Similar to rnnTimeStep and feedForward() methods.
`void`	`rnnClearPreviousState()` Clear the previous state of the RNN layers (if any), used in `rnnTimeStep(INDArray...)`
`Map<String,INDArray>`	`rnnGetPreviousState(int layer)` Get the state of the RNN layer, as used in `rnnTimeStep(INDArray...)`.
`Map<String,INDArray>`	`rnnGetPreviousState(String layerName)` Get the state of the RNN layer, as used in `rnnTimeStep(INDArray...)`.
`Map<String,Map<String,INDArray>>`	`rnnGetPreviousStates()` Get a map of states for ALL RNN layers, as used in `rnnTimeStep(INDArray...)`.
`void`	`rnnSetPreviousState(int layer, Map<String,INDArray> state)` Set the state of the RNN layer, for use in `rnnTimeStep(INDArray...)`
`void`	`rnnSetPreviousState(String layerName, Map<String,INDArray> state)` Set the state of the RNN layer, for use in `rnnTimeStep(INDArray...)`
`void`	`rnnSetPreviousStates(Map<String,Map<String,INDArray>> previousStates)` Set the states for all RNN layers, for use in `rnnTimeStep(INDArray...)`
`INDArray[]`	`rnnTimeStep(INDArray... inputs)` If this ComputationGraph contains one or more RNN layers: conduct forward pass (prediction) but using previous stored state for any RNN layers.
`INDArray[]`	`rnnTimeStep(MemoryWorkspace outputWorkspace, INDArray... inputs)` See `rnnTimeStep(INDArray...)` for details. If no memory workspace is provided, the output will be detached (not in any workspace). If a memory workspace is provided, the output activation array (i.e., the INDArray returned by this method) will be placed in the specified workspace.
`protected void`	`rnnUpdateStateWithTBPTTState()` Update the internal state of RNN layers after a truncated BPTT fit call
`void`	`save(File f)` Save the ComputationGraph to a file.
`void`	`save(File f, boolean saveUpdater)` Save the ComputationGraph to a file.
`double`	`score()` The score for the model
`double`	`score(DataSet dataSet)` Sets the input and labels and returns a score for the prediction with respect to the true labels This is equivalent to `score(DataSet, boolean)` with training==true. NOTE: this version of the score function can only be used with ComputationGraph networks that have a single input and a single output.
`double`	`score(DataSet dataSet, boolean training)` Sets the input and labels and returns a score for the prediction with respect to the true labels NOTE: this version of the score function can only be used with ComputationGraph networks that have a single input and a single output.
`double`	`score(MultiDataSet dataSet)` Score the network given the MultiDataSet, at test time
`double`	`score(MultiDataSet dataSet, boolean training)` Sets the input and labels and returns a score for the prediction with respect to the true labels
`INDArray`	`scoreExamples(DataSet data, boolean addRegularizationTerms)` Calculate the score for each example in a DataSet individually.
`INDArray`	`scoreExamples(MultiDataSet dataSet, boolean addRegularizationTerms)` Calculate the score for each example in a DataSet individually.
`void`	`setBackpropGradientsViewArray(INDArray gradient)` Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
`void`	`setCacheMode(CacheMode mode)` This method sets specified CacheMode for all layers within network
`void`	`setConf(NeuralNetConfiguration conf)` Setter for the configuration
`void`	`setGradientsAccumulator(GradientsAccumulator accumulator)` This method allows you to specificy GradientsAccumulator instance to be used with this model
`void`	`setInput(int inputNum, INDArray input)` Set the specified input for the ComputationGraph
`void`	`setInputs(INDArray... inputs)` Set all inputs for the ComputationGraph network
`void`	`setLabel(int labelNum, INDArray label)` Set the specified label for the ComputationGraph
`void`	`setLabels(INDArray... labels)` Set all labels for the ComputationGraph network
`void`	`setLastEtlTime(long time)` This method allows to set ETL field time, useful for performance tracking
`void`	`setLayerMaskArrays(INDArray[] featureMaskArrays, INDArray[] labelMaskArrays)` Set the mask arrays for features and labels.
`void`	`setLearningRate(double newLr)` Set the learning rate for all layers in the network to the specified value.
`void`	`setLearningRate(ISchedule newLr)` Set the learning rate schedule for all layers in the network to the specified schedule.
`void`	`setLearningRate(String layerName, double newLr)` Set the learning rate for a single layer in the network to the specified value.
`void`	`setLearningRate(String layerName, ISchedule newLr)` Set the learning rate schedule for a single layer in the network to the specified value. Note also that `setLearningRate(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.
`void`	`setListeners(Collection<TrainingListener> listeners)` Set the trainingListeners for the ComputationGraph (and all layers in the network)
`void`	`setListeners(TrainingListener... listeners)` Set the trainingListeners for the ComputationGraph (and all layers in the network)
`void`	`setParam(String key, INDArray val)` Set the parameter with a new ndarray
`void`	`setParams(INDArray params)` Set the parameters for this model.
`void`	`setParamsViewArray(INDArray gradient)` Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
`void`	`setParamTable(@NonNull Map<String,INDArray> paramTable)` Setter for the param table
`void`	`setScore(double score)`
`void`	`setUpdater(ComputationGraphUpdater updater)` Set the computationGraphUpdater for the network
`String`	`summary()` String detailing the architecture of the computation graph.
`String`	`summary(InputType... inputTypes)` String detailing the architecture of the computation graph.
`protected void`	`synchronizeIterEpochCounts()`
`int[]`	`topologicalSortOrder()` Calculate a topological sort order for the vertices in the graph.
`void`	`update(Gradient gradient)` Update layer weights and biases with gradient change
`void`	`update(INDArray gradient, String paramType)` Perform one update applying the gradient
`INDArray`	`updaterState()` This method returns updater state (if applicable), null otherwise
`protected void`	`validateArrayWorkspaces(LayerWorkspaceMgr mgr, INDArray array, ArrayType arrayType, String vertexName, boolean isInputVertex, String op)`

Methods inherited from class java.lang.Object
finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - configuration
```
protected ComputationGraphConfiguration configuration
```
  - initCalled
```
protected boolean initCalled
```
  - solver
```
protected transient Solver solver
```
  - flattenedParams
```
protected INDArray flattenedParams
```
  - flattenedGradients
```
protected transient INDArray flattenedGradients
```
  - gradient
```
protected Gradient gradient
```
  - score
```
protected double score
```
  - clearTbpttState
```
protected boolean clearTbpttState
```
  - helperWorkspaces
```
protected transient Map<String,org.bytedeco.javacpp.Pointer> helperWorkspaces
```
  - WS_LAYER_WORKING_MEM
```
protected static final String WS_LAYER_WORKING_MEM
```
    Workspace for working memory for a single layer: forward pass and backward pass Note that this is opened/closed once per op (activate/backpropGradient call)
    
    See Also:
    
    Constant Field Values
  - WS_ALL_LAYERS_ACT
```
protected static final String WS_ALL_LAYERS_ACT
```
    Workspace for storing all layers' activations - used only to store activations (layer inputs) as part of backprop Not used for inference
    
    See Also:
    
    Constant Field Values
  - WS_RNN_LOOP_WORKING_MEM
```
protected static final String WS_RNN_LOOP_WORKING_MEM
```
    Workspace for working memory in RNNs - opened and closed once per RNN time step
    
    See Also:
    
    Constant Field Values
  - WS_OUTPUT_MEM
```
protected static final String WS_OUTPUT_MEM
```
    Workspace for output methods that use OutputAdapter
    
    See Also:
    
    Constant Field Values
  - WS_LAYER_WORKING_MEM_CONFIG
```
protected final WorkspaceConfiguration WS_LAYER_WORKING_MEM_CONFIG
```
  - WS_ALL_LAYERS_ACT_CONFIG
```
protected static final WorkspaceConfiguration WS_ALL_LAYERS_ACT_CONFIG
```
  - WS_LAYER_ACT_X_CONFIG
```
protected final WorkspaceConfiguration WS_LAYER_ACT_X_CONFIG
```
  - WS_RNN_LOOP_WORKING_MEM_CONFIG
```
protected static final WorkspaceConfiguration WS_RNN_LOOP_WORKING_MEM_CONFIG
```
  - lastEtlTime
```
protected transient ThreadLocal<Long> lastEtlTime
```
  - vertices
```
protected GraphVertex[] vertices
```
    All GraphVertex objects in the network.
  - verticesMap
```
protected Map<String,GraphVertex> verticesMap
```
    Map of vertices by name
  - topologicalOrder
```
protected int[] topologicalOrder
```
    Indexes of graph vertices, in topological order. The topological order defines the order in which forward pass (and hence also backward pass, which is the opposite to this) is conducted in the network.
  - graphIndices
```
protected GraphIndices graphIndices
```
    Topological sort and vertex index/name + name/index mapping
  - layers
```
protected Layer[] layers
```
    A list of layers. Each of these layers is present in a GraphVertex, but are here for easy reference. This array also defines the order in which the getLayer(int) method returns layers.
- Constructor Detail
  - ComputationGraph
```
public ComputationGraph(ComputationGraphConfiguration configuration)
```
- Method Detail
  - setLastEtlTime
```
public void setLastEtlTime(long time)
```
    This method allows to set ETL field time, useful for performance tracking
    
    Parameters:
    
    time -
  - getLastEtlTime
```
public long getLastEtlTime()
```
    This method returns ETL time field value
    
    Returns:
  - setCacheMode
```
public void setCacheMode(CacheMode mode)
```
    This method sets specified CacheMode for all layers within network
    
    Parameters:
    
    mode -
  - getConfiguration
```
public ComputationGraphConfiguration getConfiguration()
```
    This method returns configuration of this ComputationGraph
    
    Returns:
  - getNumLayers
```
public int getNumLayers()
```
    Returns the number of layers in the ComputationGraph
  - getLayer
```
public Layer getLayer(int idx)
```
    Get the layer by the number of that layer, in range 0 to getNumLayers()-1 NOTE: This is different from the internal GraphVertex index for the layer
  - getLayers
```
public Layer[] getLayers()
```
    Get all layers in the ComputationGraph
  - getLayer
```
public Layer getLayer(String name)
```
    Get a given layer by name.
  - getVertices
```
public GraphVertex[] getVertices()
```
    Returns an array of all GraphVertex objects.
  - getVertex
```
public GraphVertex getVertex(String name)
```
    Return a given GraphVertex by name, or null if no vertex with that name exists
  - getNumInputArrays
```
public int getNumInputArrays()
```
    The number of inputs to this network
  - getNumOutputArrays
```
public int getNumOutputArrays()
```
    The number of output (arrays) for this network
  - setInput
```
public void setInput(int inputNum,
                     INDArray input)
```
    Set the specified input for the ComputationGraph
  - setInputs
```
public void setInputs(INDArray... inputs)
```
    Set all inputs for the ComputationGraph network
  - getInput
```
public INDArray getInput(int inputNum)
```
    Get the previously set input for the ComputationGraph
  - getInputs
```
public INDArray[] getInputs()
```
    Get the previously set inputs for the ComputationGraph
  - getInputMaskArrays
```
public INDArray[] getInputMaskArrays()
```
    Get the previously set feature/input mask arrays for the ComputationGraph
  - getLabelMaskArrays
```
public INDArray[] getLabelMaskArrays()
```
    Get the previously set label/output mask arrays for the ComputationGraph
  - setLabel
```
public void setLabel(int labelNum,
                     INDArray label)
```
    Set the specified label for the ComputationGraph
  - setLabels
```
public void setLabels(INDArray... labels)
```
    Set all labels for the ComputationGraph network
  - setGradientsAccumulator
```
public void setGradientsAccumulator(GradientsAccumulator accumulator)
```
    This method allows you to specificy GradientsAccumulator instance to be used with this model
    PLEASE NOTE: Do not use this method unless you understand how to use GradientsAccumulator & updates sharing. PLEASE NOTE: Do not use this method on standalone model
    
    Parameters:
    
    accumulator -
  - init
```
public void init()
```
    Initialize the ComputationGraph network
    
    Specified by:
    
    init in interface Model
    
    Specified by:
    
    init in interface NeuralNetwork
  - init
```
public void init(INDArray parameters,
                 boolean cloneParametersArray)
```
    Initialize the ComputationGraph, optionally with an existing parameters array. If an existing parameters array is specified, it will be used (and the values will not be modified) in the network; if no parameters array is specified, parameters will be initialized randomly according to the network configuration.
    
    Parameters:
    
    parameters - Network parameter. May be null. If null: randomly initialize.
    
    cloneParametersArray - Whether the parameter array (if any) should be cloned, or used directly
  - initGradientsView
```
public void initGradientsView()
```
    This method: initializes the flattened gradients array (used in backprop) and sets the appropriate subset in all layers. As a general rule, this shouldn't ever need to be called manually when doing training via fit(DataSet), fit(DataSetIterator) or fit(MultiDataSet) methods
  - getOutputLayerIndices
```
protected int[] getOutputLayerIndices()
```
  - pretrain
```
public void pretrain(DataSetIterator iter)
```
    Perform layerwise pretraining for one epoch - see pretrain(DataSetIterator, int)
  - pretrain
```
public void pretrain(DataSetIterator iter,
                     int numEpochs)
```
    Pretrain network with a single input and single output. DataSetIterators can only be used if the number of input arrays for the ComputationGraph is 1.
    This method performs layerwise pretraining on all pre-trainable layers in the network (VAEs, Autoencoders, etc), for the specified number of epochs each. For example, if numEpochs=3, then layer 0 will be fit for 3 epochs, followed by layer 1 for 3 epochs, and so on.
    For networks with more than one input use pretrain(MultiDataSetIterator)
  - pretrain
```
public void pretrain(MultiDataSetIterator iter)
```
    Pretrain network with multiple inputs and/or outputs
  - pretrain
```
public void pretrain(MultiDataSetIterator iter,
                     int numEpochs)
```
    Pretrain network with multiple inputs and/or outputs
    This method performs layerwise pretraining on all pre-trainable layers in the network (VAEs, Autoencoders, etc), for the specified number of epochs each. For example, if numEpochs=3, then layer 0 will be fit for 3 epochs, followed by layer 1 for 3 epochs, and so on.
    Non-pretrainable layers are ignored
    
    Parameters:
    
    iter - Training data
    
    numEpochs - Number of epochs to fit each layer with
    
    See Also:
    
    pretrainLayer(String, MultiDataSetIterator)
  - pretrainLayer
```
public void pretrainLayer(String layerName,
                          DataSetIterator dataSetIterator)
```
    Pretrain a specified layer with the given DataSetIterator
    
    Parameters:
    
    layerName - Layer name
    
    dataSetIterator - Data
  - pretrainLayer
```
public void pretrainLayer(String layerName,
                          MultiDataSetIterator iter)
```
    Pretrain a specified layer with the given MultiDataSetIterator
    
    Parameters:
    
    layerName - Layer name
    
    iter - Training data
  - fit
```
public void fit(DataSet dataSet)
```
    Fit the ComputationGraph using a DataSet. Note that this method can only be used with ComputationGraphs with 1 input and 1 output. For networks with more than one input or output, use fit(MultiDataSetIterator)
    
    Specified by:
    
    fit in interface NeuralNetwork
  - fit
```
public void fit(@NonNull
                @NonNull DataSetIterator iterator,
                int numEpochs)
```
    Perform minibatch training on all minibatches in the DataSetIterator, for the specified number of epochs. Equvalent to calling fit(DataSetIterator) numEpochs times in a loop
    
    Parameters:
    
    iterator - Training data (DataSetIterator). Iterator must support resetting
    
    numEpochs - Number of training epochs, >= 1
  - fit
```
public void fit(@NonNull
                @NonNull DataSetIterator iterator)
```
    Fit the ComputationGraph using a DataSetIterator.
    Note that this method can only be used with ComputationGraphs with 1 input and 1 output
    Method doesn't do layerwise pretraining.
    For pretraining use method pretrain.. pretrain(DataSetIterator)
    
    Specified by:
    
    fit in interface NeuralNetwork
    
    Parameters:
    
    iterator - Training data (DataSetIterator)
  - fit
```
public void fit(MultiDataSet multiDataSet)
```
    Fit the ComputationGraph using a MultiDataSet
    
    Specified by:
    
    fit in interface NeuralNetwork
  - fit
```
public void fit(@NonNull
                @NonNull MultiDataSetIterator iterator,
                int numEpochs)
```
    Perform minibatch training on all minibatches in the MultiDataSetIterator, for the specified number of epochs. Equvalent to calling fit(MultiDataSetIterator) numEpochs times in a loop
    
    Parameters:
    
    iterator - Training data (DataSetIterator). Iterator must support resetting
    
    numEpochs - Number of training epochs, >= 1
  - fit
```
public void fit(MultiDataSetIterator multi)
```
    Fit the ComputationGraph using a MultiDataSetIterator Method doesn't do layerwise pretraining.
    For pretraining use method pretrain.. pretrain(MultiDataSetIterator)
    
    Specified by:
    
    fit in interface NeuralNetwork
    
    Parameters:
    
    multi - Training data (MultiDataSetIterator)
  - fit
```
public void fit(INDArray[] inputs,
                INDArray[] labels)
```
    Fit the ComputationGraph given arrays of inputs and labels.
    
    Parameters:
    
    inputs - The network inptus
    
    labels - The labels
  - fit
```
public void fit(INDArray[] inputs,
                INDArray[] labels,
                INDArray[] featureMaskArrays,
                INDArray[] labelMaskArrays)
```
    Fit the ComputationGraph using the specified inputs and labels (and mask arrays)
    
    Parameters:
    
    inputs - The network inputs (features)
    
    labels - The network labels
    
    featureMaskArrays - Mask arrays for inputs/features. Typically used for RNN training. May be null.
    
    labelMaskArrays - Mas arrays for the labels/outputs. Typically used for RNN training. May be null.
  - topologicalSortOrder
```
public int[] topologicalSortOrder()
```
    Calculate a topological sort order for the vertices in the graph. Note that this is used for (a) working out what order to do forward pass, (b) what order to do backprop (i.e., reverse of this) (c) order to flatten parameters (and gradients)
    Specifically, gradients/params/forward pass are executed on vertex[topologicalSortOrder[i]], for i=0..nVertices-1
  - calculateIndices
```
public GraphIndices calculateIndices()
```
    Calculate the indices needed for the network:
    (a) topological sort order
    (b) Map: vertex index -> vertex name
    (c) Map: vertex name -> vertex index
    
    Returns:
    
    Calculated indices
  - computeGradientAndScore
```
public void computeGradientAndScore(LayerWorkspaceMgr workspaceMgr)
```
    Description copied from interface: Model
    
    Update the score
    
    Specified by:
    
    computeGradientAndScore in interface Model
  - computeGradientAndScore
```
public void computeGradientAndScore()
```
  - feedForward
```
public Map<String,INDArray> feedForward(INDArray input,
                                        int layerTillIndex,
                                        boolean train)
```
    Conduct forward pass using a single input array. Note that this method can only be used with ComputationGraphs with a single input array.
    
    Parameters:
    
    input - The input array
    
    layerTillIndex - the layer to feed forward to
    
    train - If true: do forward pass at training time
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(INDArray[] input,
                                        int layerTillIndex,
                                        boolean train,
                                        boolean clearInputs)
```
    Conduct forward pass using an array of inputs. This overload allows the forward pass to be conducted, optionally (not) clearing the layer input arrays.
    Note: when using clearInputs=false, there can be some performance and memory overhead: this is because the arrays are defined outside of workspaces (which are enabled by default) - otherwise, old/invalidated arrays could still be accessed after calling this method. Consequently: Don't use clearInputs=false unless you have a use case that requires them to remain after feed-forward has been completed
    
    Parameters:
    
    input - An array of ComputationGraph inputs
    
    layerTillIndex - the index of the layer to feed forward to
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    clearInputs - If true (default for other methods): clear the inputs of all layers after doing forward pass. False don't clear layer inputs.
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(INDArray[] input,
                                        int layerTillIndex,
                                        boolean train)
```
    Conduct forward pass using an array of inputs
    
    Parameters:
    
    input - An array of ComputationGraph inputs
    
    layerTillIndex - the index of the layer to feed forward to
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(boolean train,
                                        int layerTillIndex)
```
    Conduct forward pass using the stored inputs
    
    Parameters:
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    layerTillIndex - the index of the layer to feed forward to
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(INDArray input,
                                        boolean train)
```
    Conduct forward pass using a single input array. Note that this method can only be used with ComputationGraphs with a single input array.
    
    Parameters:
    
    input - The input array
    
    train - If true: do forward pass at training time
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(INDArray[] input,
                                        boolean train)
```
    Conduct forward pass using an array of inputs
    
    Parameters:
    
    input - An array of ComputationGraph inputs
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(INDArray[] input,
                                        boolean train,
                                        boolean clearInputs)
```
    Conduct forward pass using an array of inputs. This overload allows the forward pass to be conducted, optionally (not) clearing the layer input arrays.
    Note: this method should NOT be used with clearInputs = true, unless you know what you are doing. Specifically: when using clearInputs=false, in combination with workspaces, the layer input fields may leak outside of the workspaces in which they were defined - potentially causing a crash. See https://deeplearning4j.konduit.ai/config/config-memory/config-workspaces for more details
    
    Parameters:
    
    input - An array of ComputationGraph inputs
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    clearInputs - If true (default for other methods): clear the inputs of all layers after doing forward pass. False don't clear layer inputs.
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward()
```
    Conduct forward pass using the stored inputs, at test time
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(boolean train)
```
    Conduct forward pass using the stored inputs
    
    Parameters:
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    Returns:
    
    A map of activations for each layer (not each GraphVertex). Keys = layer name, values = layer activations
  - feedForward
```
public Map<String,INDArray> feedForward(boolean train,
                                        boolean excludeOutputLayers,
                                        boolean includeNonLayerVertexActivations)
```
    Parameters:
    
    train - True: training time. False: test time
    
    excludeOutputLayers - Should we exclude the output layers during forward pass? (usually: false)
    
    includeNonLayerVertexActivations - Include non-layer vertices in the output may?
    
    Returns:
    
    Map of activations. Key: vertex name. Value: activations.
  - output
```
public INDArray[] output(INDArray... input)
```
    Return an array of network outputs (predictions) at test time, given the specified network inputs Network outputs are for output layers only.
    
    Parameters:
    
    input - Inputs to the network
    
    Returns:
    
    Output activations (order: same as defined in network configuration)
  - outputSingle
```
public INDArray outputSingle(INDArray... input)
```
    A convenience method that returns a single INDArray, instead of an INDArray[]. Useful for ComputationGraphs that have only a single output. Otherwise identical to output(INDArray...)
    
    Parameters:
    
    input - Inputs to the network
    
    Returns:
    
    Output activations array
  - output
```
public INDArray[] output(boolean train,
                         INDArray... input)
```
    Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
    
    Parameters:
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    input - Inputs to the network
    
    Returns:
    
    Output activations (order: same as defined in network configuration)
  - output
```
public INDArray[] output(boolean train,
                         MemoryWorkspace outputWorkspace,
                         INDArray... input)
```
    Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
    If no memory workspace is provided, the output will be detached (not in any workspace).
    If a memory workspace is provided, the output activation array (i.e., the INDArray returned by this method) will be placed in the specified workspace. This workspace must be opened by the user before calling this method - and the user is responsible for (a) closing this workspace, and (b) ensuring the output array is not used out of scope (i.e., not used after closing the workspace to which it belongs - as this is likely to cause either an exception when used, or a crash).
    
    Parameters:
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    outputWorkspace - May be null. If not null: the workspace MUST be opened before calling this method.
    
    input - Inputs to the network
    
    Returns:
    
    Output activations (order: same as defined in network configuration)
  - output
```
public INDArray[] output(boolean train,
                         @NonNull
                         @NonNull INDArray[] input,
                         INDArray[] inputMasks)
```
    Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
    
    Parameters:
    
    train - If true: forward pass for training mode. False: test mode
    
    input - Input arrays to the netwonk
    
    inputMasks - Optional input mask arrays (may be null)
    
    Returns:
    
    Network output activations
  - output
```
public INDArray[] output(boolean train,
                         @NonNull
                         @NonNull INDArray[] input,
                         INDArray[] inputMasks,
                         INDArray[] labelMasks)
```
    Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
    
    Parameters:
    
    train - If true: forward pass for training mode. False: test mode
    
    input - Input arrays to the netwonk
    
    inputMasks - Optional input mask arrays (may be null)
    
    labelMasks - Optional label mask arrays (may be null
    
    Returns:
    
    Network output activations
  - output
```
public <T> T output(@NonNull
                    @NonNull INDArray[] inputs,
                    INDArray[] inputMasks,
                    INDArray[] labelMasks,
                    @NonNull
                    @NonNull OutputAdapter<T> outputAdapter)
```
    This method uses provided OutputAdapter to return custom object built from INDArray PLEASE NOTE: This method uses dedicated Workspace for output generation to avoid redundant allocations
    
    Type Parameters:
    
    T - T extends Object
    
    Parameters:
    
    inputs - Input arrays to the netwonk
    
    inputMasks - Optional input mask arrays (may be null)
    
    labelMasks - Optional label mask arrays (may be null
    
    outputAdapter - OutputAdapter instance
    
    Returns:
    
    T instance produced by OutputAdapter
  - output
```
public INDArray[] output(boolean train,
                         @NonNull
                         @NonNull INDArray[] input,
                         INDArray[] inputMasks,
                         INDArray[] labelMasks,
                         MemoryWorkspace outputWorkspace)
```
    Return an array of network outputs (predictions), given the specified network inputs Network outputs are for output layers only.
    If no memory workspace is provided, the output will be detached (not in any workspace).
    If a memory workspace is provided, the output activation array (i.e., the INDArray returned by this method) will be placed in the specified workspace. This workspace must be opened by the user before calling this method - and the user is responsible for (a) closing this workspace, and (b) ensuring the output array is not used out of scope (i.e., not used after closing the workspace to which it belongs - as this is likely to cause either an exception when used, or a crash).
    
    Parameters:
    
    train - If true: forward pass for training mode. False: test mode
    
    input - Input arrays to the netwonk
    
    inputMasks - Optional input mask arrays (may be null)
    
    labelMasks - Optional label mask arrays (may be null
    
    outputWorkspace - May be null. If not null: the workspace MUST be opened before calling this method.
    
    Returns:
    
    Network output activations
  - outputSingle
```
public INDArray outputSingle(boolean train,
                             INDArray... input)
```
    A convenience method that returns a single INDArray, instead of an INDArray[]. Useful for ComputationGraphs that have only a single output. Otherwise identical to output(boolean, INDArray...)
    
    Parameters:
    
    train - If true: do forward pass at training time; false: do forward pass at test time
    
    input - Inputs to the network
    
    Returns:
    
    Output activations array
  - outputSingle
```
public INDArray outputSingle(boolean train,
                             boolean clearInputs,
                             INDArray... input)
```
    Identical to outputSingle(boolean, boolean, INDArray...) but has the option of not clearing the input arrays (useful when later backpropagating external errors). Most users should use outputSingle(boolean, INDArray...) in preference to this method.
  - output
```
public INDArray[] output(boolean train,
                         boolean clearInputs,
                         INDArray... input)
```
    An output method for the network, with optional clearing of the layer inputs.
    Note: most users should use output(boolean, INDArray...) or similar methods, unless they are doing non-standard operations (like providing the input arrays externally)
    
    Parameters:
    
    train - If true: output during training. False: output during testing. Affects some things such as dropout
    
    clearInputs - If true: clear the input arrays for all layers. False: leave the input arrays as-is - which can be useful for "external errors" (no output layer) backprop use cases
    
    input - Input to the network
    
    Returns:
    
    Output from the network
  - output
```
public INDArray[] output(DataSetIterator iterator)
```
    Generate the output for all examples/batches in the input iterator, and concatenate them into a single array per network output
    
    Parameters:
    
    iterator - Data to pass through the network
    
    Returns:
    
    output for all examples in the iterator
  - output
```
public INDArray[] output(MultiDataSetIterator iterator)
```
    Generate the output for all examples/batches in the input iterator, and concatenate them into a single array per network output
    
    Parameters:
    
    iterator - Data to pass through the network
    
    Returns:
    
    output for all examples in the iterator
  - outputSingle
```
public INDArray outputSingle(DataSetIterator iterator)
```
    Generate the output for all examples/batches in the input iterator, and concatenate them into a single array. Can only be used with ComputationGraphs with 1 output
    
    Parameters:
    
    iterator - Data to pass through the network
    
    Returns:
    
    output for all examples in the iterator
  - outputSingle
```
public INDArray outputSingle(MultiDataSetIterator iterator)
```
    Generate the output for all examples/batches in the input iterator, and concatenate them into a single array. Can only be used with ComputationGraphs with 1 output
    
    Parameters:
    
    iterator - Data to pass through the network
    
    Returns:
    
    output for all examples in the iterator
  - output
```
public INDArray[] output(List<String> layers,
                         boolean train,
                         INDArray[] features,
                         INDArray[] featureMasks)
```
    Get the activations for the specific layers only
    
    Parameters:
    
    layers - Layers to get the specified activations for
    
    train - If true: train mode. False: test (inference) mode
    
    features - Features array
    
    featureMasks - Feature masks array. May be null
    
    Returns:
    
    Activations of the selected layers, in the same order as the "layers" arg/list
  - validateArrayWorkspaces
```
protected void validateArrayWorkspaces(LayerWorkspaceMgr mgr,
                                       INDArray array,
                                       ArrayType arrayType,
                                       String vertexName,
                                       boolean isInputVertex,
                                       String op)
```
  - ffToLayerActivationsDetached
```
protected Map<String,INDArray> ffToLayerActivationsDetached(boolean train,
                                                            @NonNull
                                                            @NonNull FwdPassType fwdPassType,
                                                            boolean storeLastForTBPTT,
                                                            int layerIndex,
                                                            int[] excludeIdxs,
                                                            @NonNull
                                                            @NonNull INDArray[] features,
                                                            INDArray[] fMask,
                                                            INDArray[] lMask,
                                                            boolean clearLayers)
```
    Feed-forward through the network - returning all array activations detached from any workspace. Note that no workspace should be active externally when calling this method (an exception will be thrown if a workspace is open externally)
    
    Parameters:
    
    train - Training mode (true) or test/inference mode (false)
    
    fwdPassType - Type of forward pass to perform (STANDARD or RNN_ACTIVATE_WITH_STORED_STATE only)
    
    storeLastForTBPTT - ONLY used if fwdPassType == FwdPassType.RNN_ACTIVATE_WITH_STORED_STATE
    
    layerIndex - Index (inclusive) to stop forward pass at. For all layers, use numLayers-1
    
    excludeIdxs - Layers (vertices) to exclude from forward pass. These layers will be skipped, and hence are usually output layers or at the end of the network. May be null.
    
    features - Input feature arrays
    
    fMask - Feature mask arrays. May be null.
    
    lMask - Label mask array. May be null.
    
    clearLayers - Whether the layer inputs should be cleared
    
    Returns:
    
    Map of activations (including the input), detached from any workspace
  - ffToLayerActivationsInWS
```
protected Map<String,INDArray> ffToLayerActivationsInWS(boolean train,
                                                        int layerIndex,
                                                        int[] excludeIdxs,
                                                        FwdPassType fwdPassType,
                                                        boolean storeLastForTBPTT,
                                                        INDArray[] input,
                                                        INDArray[] fMask,
                                                        INDArray[] lMask,
                                                        boolean clearInputs)
```
    Feed-forward through the network - if workspaces are used, all returned activations will be present in workspace WS_ALL_LAYERS_ACT.
    Note: if using workspaces for training, requires that WS_ALL_LAYERS_ACT is open externally. If using NO workspaces, requires that no external workspace is open
    
    Parameters:
    
    train - Training mode (true) or test/inference mode (false)
    
    layerIndex - Index (inclusive) to stop forward pass at. For all layers, use -1
    
    excludeIdxs - Layers (vertices) to exclude from forward pass. These layers will be skipped, and hence are usually output layers or at the end of the network. May be null.
    
    fwdPassType - Type of forward pass to perform (STANDARD or RNN_ACTIVATE_WITH_STORED_STATE only)
    
    storeLastForTBPTT - ONLY used if fwdPassType == FwdPassType.RNN_ACTIVATE_WITH_STORED_STATE
    
    input - Input feature arrays
    
    fMask - Feature mask arrays. May be null.
    
    lMask - Label mask array. May be null.
    
    clearInputs - Whether the layer inputs should be cleared
    
    Returns:
    
    Map of activations (including the input), in workspace WS_ALL_LAYERS_ACT if workspaces are used (detached otherwise)
  - outputOfLayersDetached
```
protected INDArray[] outputOfLayersDetached(boolean train,
                                            @NonNull
                                            @NonNull FwdPassType fwdPassType,
                                            @NonNull
                                            @NonNull int[] layerIndexes,
                                            @NonNull
                                            @NonNull INDArray[] features,
                                            INDArray[] fMask,
                                            INDArray[] lMasks,
                                            boolean clearLayerInputs,
                                            boolean detachedInputs,
                                            MemoryWorkspace outputWorkspace)
```
    Provide the output of the specified layers, detached from any workspace. This is most commonly used at inference/test time, and is more memory efficient than ffToLayerActivationsDetached(boolean, FwdPassType, boolean, int, int[], INDArray[], INDArray[], INDArray[], boolean) and ffToLayerActivationsInWS(boolean, int, int[], FwdPassType, boolean, INDArray[], INDArray[], INDArray[], boolean).
    This method clears all layer inputs. NOTE: in general, no workspaces should be activated externally for this method! This method handles the workspace activation as required
    
    Parameters:
    
    train - Training mode (true) or test/inference mode (false)
    
    fwdPassType - Type of forward pass to perform (STANDARD or RNN_TIMESTEP only)
    
    layerIndexes - Indexes of the layers to get the activations for
    
    features - Input features for the network
    
    fMask - Input/feature mask array. May be null.
    
    lMasks - Labels mask array. May be null
    
    clearLayerInputs - If true: the layer input fields will be cleared
    
    detachedInputs - If true: the layer input fields will be detached. Usually used for external errors cases
    
    outputWorkspace - Optional - if provided, outputs should be placed in this workspace. NOTE: this workspace must be open
    
    Returns:
    
    Output of the specified layers, detached from any workspace
  - backpropGradient
```
public Gradient backpropGradient(INDArray... epsilons)
```
    Calculate the gradient of the network with respect to some external errors. Note that this is typically used for things like reinforcement learning, not typical networks that include an OutputLayer or RnnOutputLayer
    
    Parameters:
    
    epsilons - Epsilons (errors) at the output. Same order with which the output layers are defined in configuration setOutputs(String...)
    
    Returns:
    
    Gradient for the network
  - calcBackpropGradients
```
protected void calcBackpropGradients(boolean clearLayers,
                                     boolean truncatedBPTT,
                                     INDArray... externalEpsilons)
```
    Do backprop (gradient calculation)
    
    Parameters:
    
    truncatedBPTT - false: normal backprop. true: calculate gradients using truncated BPTT for RNN layers
    
    externalEpsilons - null usually (for typical supervised learning). If not null (and length > 0) then assume that the user has provided some errors externally, as they would do for example in reinforcement learning situations.
  - clone
```
public ComputationGraph clone()
```
    Overrides:
    
    clone in class Object
  - calcRegularizationScore
```
public double calcRegularizationScore(boolean backpropParamsOnly)
```
  - setListeners
```
public void setListeners(Collection<TrainingListener> listeners)
```
    Set the trainingListeners for the ComputationGraph (and all layers in the network)
    
    Specified by:
    
    setListeners in interface Model
  - setListeners
```
public void setListeners(TrainingListener... listeners)
```
    Set the trainingListeners for the ComputationGraph (and all layers in the network)
    
    Specified by:
    
    setListeners in interface Model
  - addListeners
```
public void addListeners(TrainingListener... listeners)
```
    This method ADDS additional TrainingListener to existing listeners
    
    Specified by:
    
    addListeners in interface Model
    
    Parameters:
    
    listeners - Listeners to add
  - getListeners
```
public Collection<TrainingListener> getListeners()
```
    Get the trainingListeners for the ComputationGraph
  - getUpdater
```
public ComputationGraphUpdater getUpdater()
```
    Get the ComputationGraphUpdater for the network. Creates one on demand, if required
  - getUpdater
```
public ComputationGraphUpdater getUpdater(boolean initializeIfAbsent)
```
    Get the ComputationGraphUpdater for this network
    
    Parameters:
    
    initializeIfAbsent - If true: create the updater if one is absent. False: return null if absent.
    
    Returns:
    
    Updater
  - setUpdater
```
public void setUpdater(ComputationGraphUpdater updater)
```
    Set the computationGraphUpdater for the network
  - getOutputLayer
```
public Layer getOutputLayer(int outputLayerIdx)
```
    Get the specified output layer, by index. The index of the output layer may be 0 to getNumOutputArrays()-1
  - params
```
@Deprecated
public INDArray params(boolean backwardOnly)
```
    Deprecated. To be removed. Use params()
  - score
```
public double score(DataSet dataSet)
```
    Sets the input and labels and returns a score for the prediction with respect to the true labels
    This is equivalent to score(DataSet, boolean) with training==true.
    NOTE: this version of the score function can only be used with ComputationGraph networks that have a single input and a single output.
    
    Parameters:
    
    dataSet - the data to score
    
    Returns:
    
    the score for the given input,label pairs
    
    See Also:
    
    score(DataSet, boolean)
  - score
```
public double score(DataSet dataSet,
                    boolean training)
```
    Sets the input and labels and returns a score for the prediction with respect to the true labels
    NOTE: this version of the score function can only be used with ComputationGraph networks that have a single input and a single output. Use score(MultiDataSet, boolean) for multiple input/output networks
    
    Parameters:
    
    dataSet - the data to score
    
    training - whether score is being calculated at training time (true) or test time (false)
    
    Returns:
    
    the score for the given input,label pairs
    
    See Also:
    
    score(DataSet, boolean)
  - score
```
public double score(MultiDataSet dataSet)
```
    Score the network given the MultiDataSet, at test time
  - score
```
public double score(MultiDataSet dataSet,
                    boolean training)
```
    Sets the input and labels and returns a score for the prediction with respect to the true labels
    
    Parameters:
    
    dataSet - the data to score
    
    training - whether score is being calculated at training time (true) or test time (false)
    
    Returns:
    
    the score for the given input,label pairs
  - scoreExamples
```
public INDArray scoreExamples(DataSet data,
                              boolean addRegularizationTerms)
```
    Calculate the score for each example in a DataSet individually. Unlike score(DataSet) and score(DataSet, boolean) this method does not average/sum over examples. This method allows for examples to be scored individually (at test time only), which may be useful for example for autoencoder architectures and the like.
    Each row of the output (assuming addRegularizationTerms == true) is equivalent to calling score(DataSet) with a single example.
    
    Parameters:
    
    data - The data to score
    
    addRegularizationTerms - If true: add l1/l2 regularization terms (if any) to the score. If false: don't add regularization terms
    
    Returns:
    
    An INDArray (column vector) of size input.numRows(); the ith entry is the score (loss value) of the ith example
  - scoreExamples
```
public INDArray scoreExamples(MultiDataSet dataSet,
                              boolean addRegularizationTerms)
```
    Calculate the score for each example in a DataSet individually. Unlike score(MultiDataSet) and score(MultiDataSet, boolean) this method does not average/sum over examples. This method allows for examples to be scored individually (at test time only), which may be useful for example for autoencoder architectures and the like.
    Each row of the output (assuming addRegularizationTerms == true) is equivalent to calling score(MultiDataSet) with a single example.
    
    Parameters:
    
    dataSet - The data to score
    
    addRegularizationTerms - If true: add l1/l2 regularization terms (if any) to the score. If false: don't add regularization terms
    
    Returns:
    
    An INDArray (column vector) of size input.numRows(); the ith entry is the score (loss value) of the ith example
  - fit
```
public void fit()
```
    Description copied from interface: Model
    
    All models have a fit method
    
    Specified by:
    
    fit in interface Model
  - update
```
public void update(INDArray gradient,
                   String paramType)
```
    Description copied from interface: Model
    
    Perform one update applying the gradient
    
    Specified by:
    
    update in interface Model
    
    Parameters:
    
    gradient - the gradient to apply
  - update
```
public void update(Gradient gradient)
```
    Description copied from interface: Model
    
    Update layer weights and biases with gradient change
    
    Specified by:
    
    update in interface Model
  - score
```
public double score()
```
    Description copied from interface: Model
    
    The score for the model
    
    Specified by:
    
    score in interface Model
    
    Returns:
    
    the score for the model
  - setScore
```
public void setScore(double score)
```
  - params
```
public INDArray params()
```
    Description copied from interface: Model
    
    Parameters of the model (if any)
    
    Specified by:
    
    params in interface Model
    
    Specified by:
    
    params in interface NeuralNetwork
    
    Returns:
    
    the parameters of the model
  - updaterState
```
public INDArray updaterState()
```
    Description copied from interface: NeuralNetwork
    
    This method returns updater state (if applicable), null otherwise
    
    Specified by:
    
    updaterState in interface NeuralNetwork
    
    Returns:
  - numParams
```
public long numParams()
```
    Description copied from interface: Model
    
    the number of parameters for the model
    
    Specified by:
    
    numParams in interface Model
    
    Returns:
    
    the number of parameters for the model
  - numParams
```
public long numParams(boolean backwards)
```
    Description copied from interface: Model
    
    the number of parameters for the model
    
    Specified by:
    
    numParams in interface Model
    
    Returns:
    
    the number of parameters for the model
  - setParams
```
public void setParams(INDArray params)
```
    Description copied from interface: Model
    
    Set the parameters for this model. This expects a linear ndarray which then be unpacked internally relative to the expected ordering of the model
    
    Specified by:
    
    setParams in interface Model
    
    Parameters:
    
    params - the parameters for the model
  - setParamsViewArray
```
public void setParamsViewArray(INDArray gradient)
```
    Description copied from interface: Model
    
    Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
    
    Specified by:
    
    setParamsViewArray in interface Model
    
    Parameters:
    
    gradient - a 1 x nParams row vector that is a view of the larger (MLN/CG) parameters array
  - getGradientsViewArray
```
public INDArray getGradientsViewArray()
```
    Specified by:
    
    getGradientsViewArray in interface Model
  - setBackpropGradientsViewArray
```
public void setBackpropGradientsViewArray(INDArray gradient)
```
    Description copied from interface: Model
    
    Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
    
    Specified by:
    
    setBackpropGradientsViewArray in interface Model
    
    Parameters:
    
    gradient - a 1 x nParams row vector that is a view of the larger (MLN/CG) gradients array
  - fit
```
public void fit(INDArray data,
                LayerWorkspaceMgr workspaceMgr)
```
    Description copied from interface: Model
    
    Fit the model to the given data
    
    Specified by:
    
    fit in interface Model
    
    Parameters:
    
    data - the data to fit the model to
  - gradient
```
public Gradient gradient()
```
    Description copied from interface: Model
    
    Get the gradient. Note that this method will not calculate the gradient, it will rather return the gradient that has been computed before. For calculating the gradient, see Model.computeGradientAndScore(LayerWorkspaceMgr) } .
    
    Specified by:
    
    gradient in interface Model
    
    Returns:
    
    the gradient for this model, as calculated before
  - gradientAndScore
```
public Pair<Gradient,Double> gradientAndScore()
```
    Description copied from interface: Model
    
    Get the gradient and score
    
    Specified by:
    
    gradientAndScore in interface Model
    
    Returns:
    
    the gradient and score
  - batchSize
```
public int batchSize()
```
    Description copied from interface: Model
    
    The current inputs batch size
    
    Specified by:
    
    batchSize in interface Model
    
    Returns:
    
    the current inputs batch size
  - conf
```
public NeuralNetConfiguration conf()
```
    Description copied from interface: Model
    
    The configuration for the neural network
    
    Specified by:
    
    conf in interface Model
    
    Returns:
    
    the configuration for the neural network
  - setConf
```
public void setConf(NeuralNetConfiguration conf)
```
    Description copied from interface: Model
    
    Setter for the configuration
    
    Specified by:
    
    setConf in interface Model
  - input
```
public INDArray input()
```
    Description copied from interface: Model
    
    The input/feature matrix for the model
    
    Specified by:
    
    input in interface Model
    
    Returns:
    
    the input/feature matrix for the model
  - getOptimizer
```
public ConvexOptimizer getOptimizer()
```
    Description copied from interface: Model
    
    Returns this models optimizer
    
    Specified by:
    
    getOptimizer in interface Model
    
    Specified by:
    
    getOptimizer in interface NeuralNetwork
    
    Returns:
    
    this models optimizer
  - getParam
```
public INDArray getParam(String paramName)
```
    Description copied from interface: Model
    
    Get the parameter
    
    Specified by:
    
    getParam in interface Model
    
    Parameters:
    
    paramName - the key of the parameter
    
    Returns:
    
    the parameter vector/matrix with that particular key
  - paramTable
```
public Map<String,INDArray> paramTable()
```
    Description copied from interface: Model
    
    The param table
    
    Specified by:
    
    paramTable in interface Model
    
    Returns:
  - paramTable
```
public Map<String,INDArray> paramTable(boolean backpropParamsOnly)
```
    Description copied from interface: Model
    
    Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters
    
    Specified by:
    
    paramTable in interface Model
    
    Parameters:
    
    backpropParamsOnly - If true, return backprop params only. If false: return all params (equivalent to paramsTable())
  - setParamTable
```
public void setParamTable(@NonNull
                          @NonNull Map<String,INDArray> paramTable)
```
    Description copied from interface: Model
    
    Setter for the param table
    
    Specified by:
    
    setParamTable in interface Model
  - setParam
```
public void setParam(String key,
                     INDArray val)
```
    Description copied from interface: Model
    
    Set the parameter with a new ndarray
    
    Specified by:
    
    setParam in interface Model
    
    Parameters:
    
    key - the key to se t
    
    val - the new ndarray
  - clear
```
public void clear()
```
    Description copied from interface: Model
    
    Clear input
    
    Specified by:
    
    clear in interface Model
  - applyConstraints
```
public void applyConstraints(int iteration,
                             int epoch)
```
    Description copied from interface: Model
    
    Apply any constraints to the model
    
    Specified by:
    
    applyConstraints in interface Model
  - rnnTimeStep
```
public INDArray[] rnnTimeStep(INDArray... inputs)
```
    If this ComputationGraph contains one or more RNN layers: conduct forward pass (prediction) but using previous stored state for any RNN layers. The activations for the final step are also stored in the RNN layers for use next time rnnTimeStep() is called.
    This method can be used to generate output one or more steps at a time instead of always having to do forward pass from t=0. Example uses are for streaming data, and for generating samples from network output one step at a time (where samples are then fed back into the network as input)
    If no previous state is present in RNN layers (i.e., initially or after calling rnnClearPreviousState()), the default initialization (usually 0) is used.
    Supports mini-batch (i.e., multiple predictions/forward pass in parallel) as well as for single examples.
    
    Parameters:
    
    inputs - Input to network. May be for one or multiple time steps. For single time step: input has shape [miniBatchSize,inputSize] or [miniBatchSize,inputSize,1]. miniBatchSize=1 for single example.
    For multiple time steps: [miniBatchSize,inputSize,inputTimeSeriesLength]
    
    Returns:
    
    Output activations. If output is RNN layer (such as RnnOutputLayer): if all inputs have shape [miniBatchSize,inputSize] i.e., is 2d, then outputs have shape [miniBatchSize,outputSize] (i.e., also 2d) instead of [miniBatchSize,outputSize,1].
    Otherwise output is 3d [miniBatchSize,outputSize,inputTimeSeriesLength] when using RnnOutputLayer (or unmodified otherwise).
  - rnnTimeStep
```
public INDArray[] rnnTimeStep(MemoryWorkspace outputWorkspace,
                              INDArray... inputs)
```
    See rnnTimeStep(INDArray...) for details.
    If no memory workspace is provided, the output will be detached (not in any workspace).
    If a memory workspace is provided, the output activation array (i.e., the INDArray returned by this method) will be placed in the specified workspace. This workspace must be opened by the user before calling this method - and the user is responsible for (a) closing this workspace, and (b) ensuring the output array is not used out of scope (i.e., not used after closing the workspace to which it belongs - as this is likely to cause either an exception when used, or a crash).
    
    Parameters:
    
    inputs - Input activations
    
    outputWorkspace - Output workspace. May be null
    
    Returns:
    
    The output/activations from the network (either detached or in the specified workspace if provided)
  - rnnGetPreviousState
```
public Map<String,INDArray> rnnGetPreviousState(int layer)
```
    Get the state of the RNN layer, as used in rnnTimeStep(INDArray...).
    
    Parameters:
    
    layer - Number/index of the layer.
    
    Returns:
    
    Hidden state, or null if layer is not an RNN layer
  - rnnGetPreviousState
```
public Map<String,INDArray> rnnGetPreviousState(String layerName)
```
    Get the state of the RNN layer, as used in rnnTimeStep(INDArray...).
    
    Parameters:
    
    layerName - name of the layer
    
    Returns:
    
    Hidden state, or null if layer is not an RNN layer
  - rnnGetPreviousStates
```
public Map<String,Map<String,INDArray>> rnnGetPreviousStates()
```
    Get a map of states for ALL RNN layers, as used in rnnTimeStep(INDArray...). Layers that are not RNN layers will not have an entry in the returned map
    
    Returns:
    
    Map of states (keyed by layer name) or null if layer is not an RNN layer
    
    See Also:
    
    rnnSetPreviousStates(Map)
  - rnnSetPreviousState
```
public void rnnSetPreviousState(int layer,
                                Map<String,INDArray> state)
```
    Set the state of the RNN layer, for use in rnnTimeStep(INDArray...)
    
    Parameters:
    
    layer - The number/index of the layer.
    
    state - The state to set the specified layer to
  - rnnSetPreviousState
```
public void rnnSetPreviousState(String layerName,
                                Map<String,INDArray> state)
```
    Set the state of the RNN layer, for use in rnnTimeStep(INDArray...)
    
    Parameters:
    
    layerName - The name of the layer.
    
    state - The state to set the specified layer to
  - rnnSetPreviousStates
```
public void rnnSetPreviousStates(Map<String,Map<String,INDArray>> previousStates)
```
    Set the states for all RNN layers, for use in rnnTimeStep(INDArray...)
    
    Parameters:
    
    previousStates - The previous time step states for all layers (key: layer name. Value: layer states)
    
    See Also:
    
    rnnGetPreviousStates()
  - rnnClearPreviousState
```
public void rnnClearPreviousState()
```
    Clear the previous state of the RNN layers (if any), used in rnnTimeStep(INDArray...)
  - doTruncatedBPTT
```
protected void doTruncatedBPTT(INDArray[] inputs,
                               INDArray[] labels,
                               INDArray[] featureMasks,
                               INDArray[] labelMasks,
                               LayerWorkspaceMgr workspaceMgr)
```
    Fit the network using truncated BPTT
  - rnnActivateUsingStoredState
```
public Map<String,INDArray> rnnActivateUsingStoredState(INDArray[] inputs,
                                                        boolean training,
                                                        boolean storeLastForTBPTT)
```
    Similar to rnnTimeStep and feedForward() methods. Difference here is that this method:
    (a) like rnnTimeStep does forward pass using stored state for RNN layers, and
    (b) unlike rnnTimeStep does not modify the RNN layer state
    Therefore multiple calls to this method with the same input should have the same output.
    Typically used during training only. Use rnnTimeStep for prediction/forward pass at test time.
    
    Parameters:
    
    inputs - Input to network
    
    training - Whether training or not
    
    storeLastForTBPTT - set to true if used as part of truncated BPTT training
    
    Returns:
    
    Activations for each layer (including input, as per feedforward() etc)
  - setLayerMaskArrays
```
public void setLayerMaskArrays(INDArray[] featureMaskArrays,
                               INDArray[] labelMaskArrays)
```
    Set the mask arrays for features and labels. Mask arrays are typically used in situations such as one-to-many and many-to-one learning with recurrent neural networks, as well as for supporting time series of varying lengths within the same minibatch.
    For example, with RNN data sets with input of shape [miniBatchSize,nIn,timeSeriesLength] and outputs of shape [miniBatchSize,nOut,timeSeriesLength], the features and mask arrays will have shape [miniBatchSize,timeSeriesLength] and contain values 0 or 1 at each element (to specify whether a given input/example is present - or merely padding - at a given time step).
    NOTE: This method is not usually used directly. Instead, the various feedForward and fit methods handle setting of masking internally.
    
    Parameters:
    
    featureMaskArrays - Mask array for features (input)
    
    labelMaskArrays - Mask array for labels (output)
    
    See Also:
    
    clearLayerMaskArrays()
  - clearLayerMaskArrays
```
public void clearLayerMaskArrays()
```
    Remove the mask arrays from all layers.
    See setLayerMaskArrays(INDArray[], INDArray[]) for details on mask arrays.
  - rnnUpdateStateWithTBPTTState
```
protected void rnnUpdateStateWithTBPTTState()
```
    Update the internal state of RNN layers after a truncated BPTT fit call
  - evaluate
```
public <T extends Evaluation> T evaluate(DataSetIterator iterator)
```
    Evaluate the network (classification performance - single output ComputationGraphs only)
    
    Parameters:
    
    iterator - Iterator to evaluate on
    
    Returns:
    
    Evaluation object; results of evaluation on all examples in the data set
  - evaluate
```
public <T extends Evaluation> T evaluate(MultiDataSetIterator iterator)
```
    Evaluate the network (classification performance - single output ComputationGraphs only)
    
    Parameters:
    
    iterator - Iterator to evaluate on
    
    Returns:
    
    Evaluation object; results of evaluation on all examples in the data set
  - evaluate
```
public <T extends Evaluation> T evaluate(DataSetIterator iterator,
                                         List<String> labelsList)
```
    Evaluate the network on the provided data set (single output ComputationGraphs only). Used for evaluating the performance of classifiers
    
    Parameters:
    
    iterator - Data to undertake evaluation on
    
    Returns:
    
    Evaluation object, summarizing the results of the evaluation on the provided DataSetIterator
  - evaluate
```
public <T extends Evaluation> T evaluate(MultiDataSetIterator iterator,
                                         List<String> labelsList)
```
    Evaluate the network on the provided data set (single output ComputationGraphs only). Used for evaluating the performance of classifiers
    
    Parameters:
    
    iterator - Data to undertake evaluation on
    
    Returns:
    
    Evaluation object, summarizing the results of the evaluation on the provided DataSetIterator
  - evaluate
```
public <T extends Evaluation> T evaluate(DataSetIterator iterator,
                                         List<String> labelsList,
                                         int topN)
```
    Evaluate the network (for classification) on the provided data set, with top N accuracy in addition to standard accuracy. For 'standard' accuracy evaluation only, use topN = 1
    
    Parameters:
    
    iterator - Iterator (data) to evaluate on
    
    labelsList - List of labels. May be null.
    
    topN - N value for top N accuracy evaluation
    
    Returns:
    
    Evaluation object, summarizing the results of the evaluation on the provided DataSetIterator
  - evaluate
```
public <T extends Evaluation> T evaluate(MultiDataSetIterator iterator,
                                         List<String> labelsList,
                                         int topN)
```
    Evaluate the network (for classification) on the provided data set, with top N accuracy in addition to standard accuracy. For 'standard' accuracy evaluation only, use topN = 1
    
    Parameters:
    
    iterator - Iterator (data) to evaluate on
    
    labelsList - List of labels. May be null.
    
    topN - N value for top N accuracy evaluation
    
    Returns:
    
    Evaluation object, summarizing the results of the evaluation on the provided DataSetIterator
  - evaluateRegression
```
public <T extends RegressionEvaluation> T evaluateRegression(DataSetIterator iterator)
```
    Evaluate the (single output layer only) network for regression performance
    
    Parameters:
    
    iterator - Data to evaluate on
    
    Returns:
    
    Regression evaluation
  - evaluateRegression
```
public <T extends RegressionEvaluation> T evaluateRegression(MultiDataSetIterator iterator)
```
    Evaluate the (single output layer only) network for regression performance
    
    Parameters:
    
    iterator - Data to evaluate on
    
    Returns:
    
    Regression evaluation
  - evaluateRegression
```
public <T extends RegressionEvaluation> T evaluateRegression(DataSetIterator iterator,
                                                             List<String> columnNames)
```
    Evaluate the (single output layer only) network for regression performance
    
    Parameters:
    
    iterator - Data to evaluate on
    
    columnNames - Column names for the regression evaluation. May be null.
    
    Returns:
    
    Regression evaluation
  - evaluateRegression
```
public <T extends RegressionEvaluation> T evaluateRegression(MultiDataSetIterator iterator,
                                                             List<String> columnNames)
```
    Evaluate the (single output layer only) network for regression performance
    
    Parameters:
    
    iterator - Data to evaluate on
    
    Returns:
    
    Regression evaluation
  - evaluateROC
```
@Deprecated
public <T extends ROC> T evaluateROC(DataSetIterator iterator)
```
    Deprecated. To be removed - use evaluateROC(DataSetIterator, int) to enforce selection of appropriate ROC/threshold configuration
  - evaluateROC
```
public <T extends ROC> T evaluateROC(DataSetIterator iterator,
                                     int rocThresholdSteps)
```
    Evaluate the network (must be a binary classifier) on the specified data, using the ROC class
    
    Parameters:
    
    iterator - Data to evaluate on
    
    rocThresholdSteps - Number of threshold steps to use with ROC
    
    Returns:
    
    ROC evaluation on the given dataset
  - evaluateROC
```
@Deprecated
public <T extends ROC> T evaluateROC(MultiDataSetIterator iterator)
```
    Deprecated. To be removed - use evaluateROC(DataSetIterator, int) to enforce selection of appropriate ROC/threshold configuration
  - evaluateROC
```
public <T extends ROC> T evaluateROC(MultiDataSetIterator iterator,
                                     int rocThresholdSteps)
```
    Evaluate the network (must be a binary classifier) on the specified data, using the ROC class
    
    Parameters:
    
    iterator - Data to evaluate on
    
    rocThresholdSteps - Number of threshold steps to use with ROC
    
    Returns:
    
    ROC evaluation on the given dataset
  - evaluateROCMultiClass
```
@Deprecated
public <T extends ROCMultiClass> T evaluateROCMultiClass(DataSetIterator iterator)
```
    Deprecated. To be removed - use evaluateROCMultiClass(DataSetIterator, int) to enforce selection of appropriate ROC/threshold configuration
  - evaluateROCMultiClass
```
public <T extends ROCMultiClass> T evaluateROCMultiClass(DataSetIterator iterator,
                                                         int rocThresholdSteps)
```
    Evaluate the network on the specified data, using the ROCMultiClass class
    
    Parameters:
    
    iterator - Data to evaluate on
    
    rocThresholdSteps - Number of threshold steps to use with ROCMultiClass
    
    Returns:
    
    Multi-class ROC evaluation on the given dataset
  - evaluateROCMultiClass
```
public <T extends ROCMultiClass> T evaluateROCMultiClass(MultiDataSetIterator iterator,
                                                         int rocThresholdSteps)
```
    Evaluate the network on the specified data, using the ROCMultiClass class
    
    Parameters:
    
    iterator - Data to evaluate on
    
    rocThresholdSteps - Number of threshold steps to use with ROCMultiClass
    
    Returns:
    
    Multi-class ROC evaluation on the given dataset
  - doEvaluation
```
public <T extends IEvaluation> T[] doEvaluation(DataSetIterator iterator,
                                                T... evaluations)
```
    Perform evaluation on the given data (DataSetIterator) with the given IEvaluation instance
    
    Specified by:
    
    doEvaluation in interface NeuralNetwork
    
    Type Parameters:
    
    T - Type of the IEvaluation instance
    
    Parameters:
    
    iterator - Test data to evaluate on
    
    evaluations - IEvaluation instances
    
    Returns:
    
    The input IEvaluation instance, after performing evaluation on the test data
  - doEvaluation
```
public <T extends IEvaluation> T[] doEvaluation(MultiDataSetIterator iterator,
                                                T... evaluations)
```
    Perform evaluation on the given data (MultiDataSetIterator) with the given IEvaluation instance
    
    Specified by:
    
    doEvaluation in interface NeuralNetwork
    
    Type Parameters:
    
    T - Type of the IEvaluation instance
    
    Parameters:
    
    iterator - Test data to evaluate on
    
    evaluations - IEvaluation insntance
    
    Returns:
    
    The input IEvaluation instance, after performing evaluation on the test data
  - evaluate
```
public <T extends IEvaluation> Map<Integer,T[]> evaluate(DataSetIterator iterator,
                                                         Map<Integer,T[]> evaluations)
```
    Perform evaluation for networks with multiple outputs.
    
    Parameters:
    
    iterator - Data to evaluate
    
    evaluations - Evaluation instances. Key: the network output number (0 to numOutputs-1). Value: the IEvaluation instances to perform evaluation with, for that output only. Note that not every output needs to have an IEvaluation[] defined.
    
    Returns:
    
    The same evaluation map, after performing evaluation
  - evaluate
```
public <T extends IEvaluation> Map<Integer,T[]> evaluate(MultiDataSetIterator iterator,
                                                         Map<Integer,T[]> evaluations)
```
    Perform evaluation for networks with multiple outputs.
    
    Parameters:
    
    iterator - Data to evaluate
    
    evaluations - Evaluation instances. Key: the network output number (0 to numOutputs-1). Value: the IEvaluation instances to perform evaluation with, for that output only. Note that not every output needs to have an IEvaluation[] defined.
    
    Returns:
    
    The same evaluation map, after performing evaluation
  - summary
```
public String summary()
```
    String detailing the architecture of the computation graph. Vertices are printed in a topological sort order. Columns are Vertex Names with layer/vertex type, nIn, nOut, Total number of parameters and the Shapes of the parameters And the inputs to the vertex Will also give information about frozen layers/vertices, if any.
    
    Returns:
    
    Summary as a string
    
    See Also:
    
    memoryInfo(int, InputType...)
  - summary
```
public String summary(InputType... inputTypes)
```
    String detailing the architecture of the computation graph. Will also display activation size when given an input type. Vertices are printed in a topological sort order. Columns are Vertex Names with layer/vertex type, nIn, nOut, Total number of parameters and the Shapes of the parameters And the inputs to the vertex Will also give information about frozen layers/vertices, if any.
    
    Returns:
    
    Summary as a string
    
    See Also:
    
    memoryInfo(int, InputType...)
  - memoryInfo
```
public String memoryInfo(int minibatch,
                         InputType... inputTypes)
```
    Generate information regarding memory use for the network, for the given input types and minibatch size. Note that when using workspaces or CuDNN, the network should be trained for some iterations so that the memory workspaces have time to initialize. Without this, the memory requirements during training may be underestimated. Note also that this is the same information that is generated during an OOM crash when training or performing inference.
    
    Parameters:
    
    minibatch - Minibatch size to estimate memory for
    
    inputTypes - Input types to the network
    
    Returns:
    
    A String with information about network memory use information
  - clearLayersStates
```
public void clearLayersStates()
```
    This method just makes sure there's no state preserved within layers
  - incrementEpochCount
```
public void incrementEpochCount()
```
    Increment the epoch count (in the underlying ComputationGraphConfiguration by 1). Note that this is done automatically when using iterator-based fitting methods, such as fit(DataSetIterator) or fit(MultiDataSet). However, when using non-iterator fit methods (DataSet, MultiDataSet, INDArrays etc), the network has no way to know when one epoch ends and another starts. In such situations, this method can be used to increment the epoch counter.
    Note that the epoch counter is used for situations such as some learning rate schedules, and the like. The current epoch count can be obtained using ComputationGraph.getConfiguration().getEpochCount()
  - synchronizeIterEpochCounts
```
protected void synchronizeIterEpochCounts()
```
  - getIterationCount
```
public int getIterationCount()
```
    Returns the number of iterations (parameter updates) that the ComputationGraph has done
    
    Returns:
    
    Number of iterations
  - getEpochCount
```
public int getEpochCount()
```
    Returns the number of epochs that the ComputationGraph has done. Note that the epoch count is incremented only when fit(DataSetIterator), fit(MultiDataSetIterator), fit(DataSetIterator, int) or fit(MultiDataSetIterator, int) are used. The epoch count can also be manually incremented using incrementEpochCount()
    
    Returns:
    
    Number of epochs
  - save
```
public void save(File f)
          throws IOException
```
    Save the ComputationGraph to a file. Restore using load(File, boolean). Note that this saves the updater (i.e., the state array for momentum/Adam/rmsprop etc), which is desirable if further training will be undertaken.
    
    Parameters:
    
    f - File to save the network to
    
    Throws:
    
    IOException
    
    See Also:
    
    ModelSerializer for more details (and saving/loading via streams), save(File, boolean)
  - save
```
public void save(File f,
                 boolean saveUpdater)
          throws IOException
```
    Save the ComputationGraph to a file. Restore using load(File, boolean).
    
    Parameters:
    
    f - File to save the network to
    
    saveUpdater - If true: save the updater (i.e., the state array for momentum/Adam/rmsprop etc), which should usually be saved if further training is required
    
    Throws:
    
    IOException
    
    See Also:
    
    ModelSerializer for more details (and saving/loading via streams), save(File, boolean)
  - load
```
public static ComputationGraph load(File f,
                                    boolean loadUpdater)
                             throws IOException
```
    Restore a ComputationGraph to a file, saved using save(File) or ModelSerializer
    
    Parameters:
    
    f - File to load the network from
    
    loadUpdater - If true: load the updater if it is available (i.e., the state array for momentum/Adam/rmsprop etc) - use false if no further training is required, or true if further training will be undertaken
    
    Throws:
    
    IOException
    
    See Also:
    
    ModelSerializer for more details (and saving/loading via streams)
  - convertDataType
```
public ComputationGraph convertDataType(@NonNull
                                        @NonNull DataType dataType)
```
    Return a copy of the network with the parameters and activations set to use the specified (floating point) data type. If the existing datatype is the same as the requested dataype, the original network will be returned unchanged. Only floating point datatypes (DOUBLE, FLOAT, HALF) may be used.
    
    Parameters:
    
    dataType - Datatype to convert the network to
    
    Returns:
    
    The network, set to use the specified datatype for the parameters and activations
  - setLearningRate
```
public void setLearningRate(double newLr)
```
    Set the learning rate for all layers in the network to the specified value. Note that if any learning rate schedules are currently present, these will be removed in favor of the new (fixed) learning rate.
    
    Note: This method not free from a performance point of view: a proper learning rate schedule should be used in preference to calling this method at every iteration.
    
    Parameters:
    
    newLr - New learning rate for all layers
    
    See Also:
    
    setLearningRate(ISchedule), setLearningRate(String, double)
  - setLearningRate
```
public void setLearningRate(ISchedule newLr)
```
    Set the learning rate schedule for all layers in the network to the specified schedule. This schedule will replace any/all existing schedules, and also any fixed learning rate values.
    Note that the iteration/epoch counts will not be reset. Use ComputationGraphConfiguration#setIterationCount(int) and ComputationGraphConfiguration#setEpochCount(int) if this is required
    
    Parameters:
    
    newLr - New learning rate schedule for all layers
    
    See Also:
    
    setLearningRate(ISchedule), setLearningRate(String, double)
  - setLearningRate
```
public void setLearningRate(String layerName,
                            double newLr)
```
    Set the learning rate for a single layer in the network to the specified value. Note that if any learning rate schedules are currently present, these will be removed in favor of the new (fixed) learning rate.
    
    Note: This method not free from a performance point of view: a proper learning rate schedule should be used in preference to calling this method at every iteration. Note also that setLearningRate(double) should also be used in preference, when all layers need to be set to a new LR
    
    Parameters:
    
    layerName - Name of the layer to set the LR for
    
    newLr - New learning rate for a single layer
    
    See Also:
    
    setLearningRate(ISchedule), setLearningRate(String, double)
  - setLearningRate
```
public void setLearningRate(String layerName,
                            ISchedule newLr)
```
    Set the learning rate schedule for a single layer in the network to the specified value.
    Note also that setLearningRate(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. Use ComputationGraphConfiguration#setIterationCount(int) and ComputationGraphConfiguration#setEpochCount(int) if this is required
    
    Parameters:
    
    layerName - Name of the layer to set the LR schedule for
    
    newLr - New learning rate for a single layer
    
    See Also:
    
    setLearningRate(ISchedule), setLearningRate(String, double)
  - getLearningRate
```
public Double getLearningRate(String layerName)
```
    Get the current learning rate, for the specified layer, from the network. Note: If the layer has no learning rate (no parameters, or an updater without a learning rate) then null is returned
    
    Parameters:
    
    layerName - Layer name
    
    Returns:
    
    Learning rate for the specified layer, or null
  - layerSize
```
public long layerSize(int layer)
```
    Return the layer size (number of units) for the specified layer. Note that the meaning of the "layer size" can depend on the type of layer. For example:
    - DenseLayer, OutputLayer, recurrent layers: number of units (nOut configuration option)
    - ConvolutionLayer: the channels (number of channels)
    - Subsampling layers, global pooling layers, etc: size of 0 is always returned
    
    Parameters:
    
    layer - Index of the layer to get the size of. Must be in range 0 to nLayers-1 inclusive
    
    Returns:
    
    Size of the layer
  - layerInputSize
```
public long layerInputSize(int layer)
```
    Return the input size (number of inputs) for the specified layer.
    Note that the meaning of the "input size" can depend on the type of layer. For example:
    - DenseLayer, OutputLayer, etc: the feature vector size (nIn configuration option)
    - Recurrent layers: the feature vector size per time step (nIn configuration option)
    - ConvolutionLayer: the channels (number of channels)
    - Subsampling layers, global pooling layers, etc: size of 0 is always returned
    
    Parameters:
    
    layer - Index of the layer to get the size of. Must be in range 0 to nLayers-1 inclusive
    
    Returns:
    
    Size of the layer
  - layerSize
```
public long layerSize(String layerName)
```
    Return the layer size (number of units) for the specified layer.
    Note that the meaning of the "layer size" can depend on the type of layer. For example:
    - DenseLayer, OutputLayer, recurrent layers: number of units (nOut configuration option)
    - ConvolutionLayer: the channels (number of channels)
    - Subsampling layers, global pooling layers, etc: size of 0 is always returned
    
    Parameters:
    
    layerName - Name of the layer to get the size of
    
    Returns:
    
    Size of the layer
  - layerInputSize
```
public long layerInputSize(String layerName)
```
    Return the input size (number of inputs) for the specified layer.
    Note that the meaning of the "input size" can depend on the type of layer. For example:
    - DenseLayer, OutputLayer, etc: the feature vector size (nIn configuration option)
    - Recurrent layers: the feature vector size per time step (nIn configuration option)
    - ConvolutionLayer: the channels (number of channels)
    - Subsampling layers, global pooling layers, etc: size of 0 is always returned
    
    Parameters:
    
    layerName - Name of the layer to get the size of
    
    Returns:
    
    Size of the layer
  - equals
```
public boolean equals(Object obj)
```
    Indicates whether some other object is "equal to" this one.
    The equals method implements an equivalence relation on non-null object references:
    - It is reflexive: for any non-null reference value x, x.equals(x) should return true.
    - It is symmetric: for any non-null reference values x and y, x.equals(y) should return true if and only if y.equals(x) returns true.
    - It is transitive: for any non-null reference values x, y, and z, if x.equals(y) returns true and y.equals(z) returns true, then x.equals(z) should return true.
    - It is consistent: for any non-null reference values x and y, multiple invocations of x.equals(y) consistently return true or consistently return false, provided no information used in equals comparisons on the objects is modified.
    - For any non-null reference value x, x.equals(null) should return false.
    The equals method for class Object implements the most discriminating possible equivalence relation on objects; that is, for any non-null reference values x and y, this method returns true if and only if x and y refer to the same object (x == y has the value true).
    Note that it is generally necessary to override the hashCode method whenever this method is overridden, so as to maintain the general contract for the hashCode method, which states that equal objects must have equal hash codes.
    Overrides:
    
    equals in class Object
    
    Parameters:
    
    obj - the reference object with which to compare.
    
    Returns:
    
    true if this object is the same as the obj argument; false otherwise.
    
    See Also:
    
    Object.hashCode(), HashMap
  - close
```
public void close()
```
    Close the network and deallocate all native memory, including: parameters, gradients, updater memory and workspaces Note that the network should not be used again for any purpose after it has been closed
    
    Specified by:
    
    close in interface Model

Class ComputationGraph

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

configuration

initCalled

solver

flattenedParams

flattenedGradients

gradient

score

clearTbpttState

helperWorkspaces

WS_LAYER_WORKING_MEM

WS_ALL_LAYERS_ACT

WS_RNN_LOOP_WORKING_MEM

WS_OUTPUT_MEM

WS_LAYER_WORKING_MEM_CONFIG

WS_ALL_LAYERS_ACT_CONFIG

WS_LAYER_ACT_X_CONFIG

WS_RNN_LOOP_WORKING_MEM_CONFIG

lastEtlTime

vertices

verticesMap

topologicalOrder

graphIndices

layers

Constructor Detail

ComputationGraph

Method Detail

setLastEtlTime

getLastEtlTime

setCacheMode

getConfiguration

getNumLayers

getLayer

getLayers

getLayer

getVertices

getVertex

getNumInputArrays

getNumOutputArrays

setInput

setInputs

getInput

getInputs

getInputMaskArrays

getLabelMaskArrays

setLabel

setLabels

setGradientsAccumulator

init

init

initGradientsView

getOutputLayerIndices

pretrain

pretrain

pretrain

pretrain

pretrainLayer

pretrainLayer

fit

fit

fit

fit

fit

fit

fit

fit

topologicalSortOrder

calculateIndices

computeGradientAndScore

computeGradientAndScore

feedForward

feedForward

feedForward

feedForward

feedForward