Uses of Interface
org.deeplearning4j.nn.api.Layer

Packages that use Layer

Package	Description
org.deeplearning4j.gradientcheck
org.deeplearning4j.nn.api
org.deeplearning4j.nn.api.layers
org.deeplearning4j.nn.conf.layers
org.deeplearning4j.nn.conf.layers.misc
org.deeplearning4j.nn.conf.layers.variational
org.deeplearning4j.nn.graph
org.deeplearning4j.nn.graph.vertex
org.deeplearning4j.nn.graph.vertex.impl
org.deeplearning4j.nn.graph.vertex.impl.rnn
org.deeplearning4j.nn.layers
org.deeplearning4j.nn.layers.convolution
org.deeplearning4j.nn.layers.convolution.subsampling
org.deeplearning4j.nn.layers.feedforward.autoencoder
org.deeplearning4j.nn.layers.feedforward.dense
org.deeplearning4j.nn.layers.feedforward.embedding
org.deeplearning4j.nn.layers.feedforward.rbm
org.deeplearning4j.nn.layers.normalization
org.deeplearning4j.nn.layers.pooling
org.deeplearning4j.nn.layers.recurrent
org.deeplearning4j.nn.layers.training
org.deeplearning4j.nn.layers.variational
org.deeplearning4j.nn.multilayer
org.deeplearning4j.nn.updater
org.deeplearning4j.nn.updater.graph
org.deeplearning4j.util

Uses of Layer in org.deeplearning4j.gradientcheck

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

Modifier and Type	Method and Description
static boolean	GradientCheckUtil.checkGradientsPretrainLayer(Layer layer, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, org.nd4j.linalg.api.ndarray.INDArray input, int rngSeed) Check backprop gradients for a pretrain layer NOTE: gradient checking pretrain layers can be difficult...

Uses of Layer in org.deeplearning4j.nn.api

Methods in org.deeplearning4j.nn.api that return Layer

Modifier and Type	Method and Description
Layer	Layer.clone() Clone the layer
Layer[]	NeuralNetworkPrototype.getLayers()
Layer	Layer.transpose() Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)

Methods in org.deeplearning4j.nn.api with parameters of type Layer

Modifier and Type	Method and Description
void	Layer.merge(Layer layer, int batchSize) Deprecated. As of 0.7.3 - Feb 2017. No longer used. Merging (for parameter averaging) done via alternative means
void	Updater.setStateViewArray(Layer layer, org.nd4j.linalg.api.ndarray.INDArray viewArray, boolean initialize) Set the internal (historical) state view array for this updater
void	Updater.update(Layer layer, Gradient gradient, int iteration, int miniBatchSize) Updater: updates the model

Uses of Layer in org.deeplearning4j.nn.api.layers

Subinterfaces of Layer in org.deeplearning4j.nn.api.layers

Modifier and Type	Interface and Description
interface	IOutputLayer Interface for output layers (those that calculate gradients with respect to a labels array)
interface	RecurrentLayer Created by Alex on 28/08/2016.

Uses of Layer in org.deeplearning4j.nn.conf.layers

Methods in org.deeplearning4j.nn.conf.layers that return Layer

Modifier and Type	Method and Description
Layer	AutoEncoder.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	SubsamplingLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	OutputLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
abstract Layer	Layer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	LSTM.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	RBM.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	EmbeddingLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	BatchNormalization.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	RnnOutputLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	GravesBidirectionalLSTM.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	GravesLSTM.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	GlobalPoolingLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	ActivationLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	LocalResponseNormalization.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	ConvolutionLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	DropoutLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	CenterLossOutputLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	Subsampling1DLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	LossLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	Convolution1DLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	ZeroPaddingLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)
Layer	DenseLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)

Uses of Layer in org.deeplearning4j.nn.conf.layers.misc

Methods in org.deeplearning4j.nn.conf.layers.misc that return Layer

Modifier and Type	Method and Description
Layer	FrozenLayer.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)

Uses of Layer in org.deeplearning4j.nn.conf.layers.variational

Methods in org.deeplearning4j.nn.conf.layers.variational that return Layer

Modifier and Type	Method and Description
Layer	VariationalAutoencoder.instantiate(NeuralNetConfiguration conf, Collection<IterationListener> iterationListeners, int layerIndex, org.nd4j.linalg.api.ndarray.INDArray layerParamsView, boolean initializeParams)

Uses of Layer in org.deeplearning4j.nn.graph

Fields in org.deeplearning4j.nn.graph declared as Layer

Modifier and Type	Field and Description
protected Layer[]	ComputationGraph.layers A list of layers.

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

Modifier and Type	Method and Description
Layer	ComputationGraph.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	ComputationGraph.getLayer(String name) Get a given layer by name.
Layer[]	ComputationGraph.getLayers() Get all layers in the ComputationGraph
Layer	ComputationGraph.getOutputLayer(int outputLayerIdx) Get the specified output layer, by index.

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

Methods in org.deeplearning4j.nn.graph.vertex that return Layer

Modifier and Type	Method and Description
Layer	GraphVertex.getLayer() Get the Layer (if any).

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

Methods in org.deeplearning4j.nn.graph.vertex.impl that return Layer

Modifier and Type	Method and Description
Layer	ScaleVertex.getLayer()
Layer	PreprocessorVertex.getLayer()
Layer	PoolHelperVertex.getLayer()
Layer	LayerVertex.getLayer()
Layer	MergeVertex.getLayer()
Layer	InputVertex.getLayer()
Layer	L2NormalizeVertex.getLayer()
Layer	SubsetVertex.getLayer()
Layer	ShiftVertex.getLayer()
Layer	ElementWiseVertex.getLayer()
Layer	UnstackVertex.getLayer()
Layer	StackVertex.getLayer()
Layer	L2Vertex.getLayer()
Layer	ReshapeVertex.getLayer()

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

Constructor and Description
LayerVertex(ComputationGraph graph, String name, int vertexIndex, Layer layer, InputPreProcessor layerPreProcessor, boolean outputVertex) Create a network input vertex:
LayerVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, Layer layer, InputPreProcessor layerPreProcessor, boolean outputVertex)

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

Methods in org.deeplearning4j.nn.graph.vertex.impl.rnn that return Layer

Modifier and Type	Method and Description
Layer	DuplicateToTimeSeriesVertex.getLayer()
Layer	LastTimeStepVertex.getLayer()

Uses of Layer in org.deeplearning4j.nn.layers

Classes in org.deeplearning4j.nn.layers that implement Layer

Modifier and Type	Class and Description
class	AbstractLayer<LayerConfT extends Layer> A layer with input and output, no parameters or gradients
class	ActivationLayer Activation Layer Used to apply activation on input and corresponding derivative on epsilon.
class	BaseLayer<LayerConfT extends BaseLayer> A layer with parameters
class	BaseOutputLayer<LayerConfT extends BaseOutputLayer> Output layer with different objective in co-occurrences for different objectives.
class	BasePretrainNetwork<LayerConfT extends BasePretrainNetwork> Baseline class for any Neural Network used as a layer in a deep network *
class	DropoutLayer Created by davekale on 12/7/16.
class	FrozenLayer For purposes of transfer learning A frozen layers wraps another dl4j layer within it.
class	LossLayer LossLayer is a flexible output "layer" that performs a loss function on an input without MLP logic.
class	OutputLayer Output layer with different objective incooccurrences for different objectives.

Methods in org.deeplearning4j.nn.layers that return Layer

Modifier and Type	Method and Description
Layer	FrozenLayer.clone()
Layer	ActivationLayer.clone()
abstract Layer	AbstractLayer.clone()
Layer	BaseLayer.clone()
Layer	FrozenLayer.getInsideLayer()
Layer	FrozenLayer.transpose()
Layer	ActivationLayer.transpose()
Layer	DropoutLayer.transpose()
Layer	AbstractLayer.transpose()
Layer	LossLayer.transpose()
Layer	BaseLayer.transpose()

Methods in org.deeplearning4j.nn.layers with parameters of type Layer

Modifier and Type	Method and Description
void	FrozenLayer.merge(Layer layer, int batchSize)
void	ActivationLayer.merge(Layer layer, int batchSize)
void	DropoutLayer.merge(Layer layer, int batchSize)
void	AbstractLayer.merge(Layer l, int batchSize) Averages the given logistic regression from a mini batch into this layer
void	LossLayer.merge(Layer layer, int batchSize)
void	BaseLayer.merge(Layer l, int batchSize) Averages the given logistic regression from a mini batch into this layer

Constructors in org.deeplearning4j.nn.layers with parameters of type Layer

Constructor and Description
FrozenLayer(Layer insideLayer)

Uses of Layer in org.deeplearning4j.nn.layers.convolution

Classes in org.deeplearning4j.nn.layers.convolution that implement Layer

Modifier and Type	Class and Description
class	Convolution1DLayer 1D (temporal) convolutional layer.
class	ConvolutionLayer Convolution layer
class	ZeroPaddingLayer Zero padding layer for convolutional neural networks.

Methods in org.deeplearning4j.nn.layers.convolution that return Layer

Modifier and Type	Method and Description
Layer	ZeroPaddingLayer.clone()
Layer	ConvolutionLayer.transpose()

Methods in org.deeplearning4j.nn.layers.convolution with parameters of type Layer

Modifier and Type	Method and Description
void	ConvolutionLayer.merge(Layer layer, int batchSize)

Uses of Layer in org.deeplearning4j.nn.layers.convolution.subsampling

Classes in org.deeplearning4j.nn.layers.convolution.subsampling that implement Layer

Modifier and Type	Class and Description
class	Subsampling1DLayer 1D (temporal) subsampling layer.
class	SubsamplingLayer Subsampling layer.

Methods in org.deeplearning4j.nn.layers.convolution.subsampling that return Layer

Modifier and Type	Method and Description
Layer	SubsamplingLayer.clone()
Layer	SubsamplingLayer.transpose()

Methods in org.deeplearning4j.nn.layers.convolution.subsampling with parameters of type Layer

Modifier and Type	Method and Description
void	SubsamplingLayer.merge(Layer layer, int batchSize)

Uses of Layer in org.deeplearning4j.nn.layers.feedforward.autoencoder

Classes in org.deeplearning4j.nn.layers.feedforward.autoencoder that implement Layer

Modifier and Type	Class and Description
class	AutoEncoder Autoencoder.

Uses of Layer in org.deeplearning4j.nn.layers.feedforward.dense

Classes in org.deeplearning4j.nn.layers.feedforward.dense that implement Layer

Modifier and Type	Class and Description
class	DenseLayer

Uses of Layer in org.deeplearning4j.nn.layers.feedforward.embedding

Classes in org.deeplearning4j.nn.layers.feedforward.embedding that implement Layer

Modifier and Type	Class and Description
class	EmbeddingLayer Embedding layer: feed-forward layer that expects single integers per example as input (class numbers, in range 0 to numClass-1) as input.

Uses of Layer in org.deeplearning4j.nn.layers.feedforward.rbm

Classes in org.deeplearning4j.nn.layers.feedforward.rbm that implement Layer

Modifier and Type	Class and Description
class	RBM Restricted Boltzmann Machine.

Methods in org.deeplearning4j.nn.layers.feedforward.rbm that return Layer

Modifier and Type	Method and Description
Layer	RBM.transpose() Deprecated.

Uses of Layer in org.deeplearning4j.nn.layers.normalization

Classes in org.deeplearning4j.nn.layers.normalization that implement Layer

Modifier and Type	Class and Description
class	BatchNormalization Batch normalization layer.
class	LocalResponseNormalization Deep neural net normalization approach normalizes activations between layers "brightness normalization" Used for nets like AlexNet

Methods in org.deeplearning4j.nn.layers.normalization that return Layer

Modifier and Type	Method and Description
Layer	BatchNormalization.clone()
Layer	LocalResponseNormalization.clone()
Layer	BatchNormalization.transpose()
Layer	LocalResponseNormalization.transpose()

Methods in org.deeplearning4j.nn.layers.normalization with parameters of type Layer

Modifier and Type	Method and Description
void	BatchNormalization.merge(Layer layer, int batchSize)
void	LocalResponseNormalization.merge(Layer layer, int batchSize)

Uses of Layer in org.deeplearning4j.nn.layers.pooling

Classes in org.deeplearning4j.nn.layers.pooling that implement Layer

Modifier and Type	Class and Description
class	GlobalPoolingLayer Global pooling layer - used to do pooling over time for RNNs, and 2d pooling for CNNs. Supports the following PoolingTypes: SUM, AVG, MAX, PNORM Global pooling layer can also handle mask arrays when dealing with variable length inputs.

Methods in org.deeplearning4j.nn.layers.pooling that return Layer

Modifier and Type	Method and Description
Layer	GlobalPoolingLayer.clone()

Uses of Layer in org.deeplearning4j.nn.layers.recurrent

Classes in org.deeplearning4j.nn.layers.recurrent that implement Layer

Modifier and Type	Class and Description
class	BaseRecurrentLayer<LayerConfT extends BaseLayer>
class	GravesBidirectionalLSTM RNN tutorial: http://deeplearning4j.org/usingrnns.html READ THIS FIRST Bdirectional LSTM layer implementation.
class	GravesLSTM LSTM layer implementation.
class	LSTM LSTM layer implementation.
class	RnnOutputLayer Recurrent Neural Network Output Layer. Handles calculation of gradients etc for various objective functions. Functionally the same as OutputLayer, but handles output and label reshaping automatically. Input and output activations are same as other RNN layers: 3 dimensions with shape [miniBatchSize,nIn,timeSeriesLength] and [miniBatchSize,nOut,timeSeriesLength] respectively.

Methods in org.deeplearning4j.nn.layers.recurrent that return Layer

Modifier and Type	Method and Description
Layer	LSTM.transpose()
Layer	GravesBidirectionalLSTM.transpose()
Layer	GravesLSTM.transpose()

Methods in org.deeplearning4j.nn.layers.recurrent with parameters of type Layer

Modifier and Type

Method and Description

FwdPassReturn

LSTMHelper.activate(Layer layer, NeuralNetConfiguration conf, org.nd4j.linalg.activations.IActivation gateActivationFn, org.nd4j.linalg.api.ndarray.INDArray input, org.nd4j.linalg.api.ndarray.INDArray recurrentWeights, org.nd4j.linalg.api.ndarray.INDArray inputWeights, org.nd4j.linalg.api.ndarray.INDArray biases, boolean training, org.nd4j.linalg.api.ndarray.INDArray prevOutputActivations, org.nd4j.linalg.api.ndarray.INDArray prevMemCellState, boolean forBackprop, boolean forwards, String inputWeightKey, org.nd4j.linalg.api.ndarray.INDArray maskArray, boolean hasPeepholeConnections)

Uses of Layer in org.deeplearning4j.nn.layers.training

Classes in org.deeplearning4j.nn.layers.training that implement Layer

Modifier and Type	Class and Description
class	CenterLossOutputLayer Center loss is similar to triplet loss except that it enforces intraclass consistency and doesn't require feed forward of multiple examples.

Uses of Layer in org.deeplearning4j.nn.layers.variational

Classes in org.deeplearning4j.nn.layers.variational that implement Layer

Modifier and Type	Class and Description
class	VariationalAutoencoder Variational Autoencoder layer

Methods in org.deeplearning4j.nn.layers.variational that return Layer

Modifier and Type	Method and Description
Layer	VariationalAutoencoder.clone()
Layer	VariationalAutoencoder.transpose()

Methods in org.deeplearning4j.nn.layers.variational with parameters of type Layer

Modifier and Type	Method and Description
void	VariationalAutoencoder.merge(Layer layer, int batchSize)

Uses of Layer in org.deeplearning4j.nn.multilayer

Classes in org.deeplearning4j.nn.multilayer that implement Layer

Modifier and Type	Class and Description
class	MultiLayerNetwork MultiLayerNetwork is a neural network with multiple layers in a stack, and usually an output layer.

Fields in org.deeplearning4j.nn.multilayer declared as Layer

Modifier and Type	Field and Description
protected Layer[]	MultiLayerNetwork.layers

Fields in org.deeplearning4j.nn.multilayer with type parameters of type Layer

Modifier and Type	Field and Description
protected LinkedHashMap<String,Layer>	MultiLayerNetwork.layerMap

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

Modifier and Type	Method and Description
Layer	MultiLayerNetwork.getLayer(int i)
Layer	MultiLayerNetwork.getLayer(String name)
Layer[]	MultiLayerNetwork.getLayers()
Layer	MultiLayerNetwork.getOutputLayer() Get the output layer
Layer	MultiLayerNetwork.transpose()

Methods in org.deeplearning4j.nn.multilayer with parameters of type Layer

Modifier and Type	Method and Description
void	MultiLayerNetwork.merge(Layer layer, int batchSize) Deprecated. Not supported and not used
void	MultiLayerNetwork.setLayers(Layer[] layers)

Uses of Layer in org.deeplearning4j.nn.updater

Fields in org.deeplearning4j.nn.updater with type parameters of type Layer

Modifier and Type	Field and Description
protected Map<String,Layer>	BaseMultiLayerUpdater.layersByName

Methods in org.deeplearning4j.nn.updater that return Layer

Modifier and Type	Method and Description
protected abstract Layer[]	BaseMultiLayerUpdater.getOrderedLayers()
protected Layer[]	MultiLayerUpdater.getOrderedLayers()
protected Layer[]	LayerUpdater.getOrderedLayers()

Methods in org.deeplearning4j.nn.updater with parameters of type Layer

Modifier and Type	Method and Description
static boolean	UpdaterUtils.lrSchedulesEqual(Layer layer1, String param1, Layer layer2, String param2)
void	UpdaterBlock.postApply(Layer layer, String paramName, org.nd4j.linalg.api.ndarray.INDArray gradientView, org.nd4j.linalg.api.ndarray.INDArray paramsView) Apply L1 and L2 regularization, if necessary.
void	BaseMultiLayerUpdater.preApply(Layer layer, Gradient gradient, int iteration) Pre-apply: Apply gradient normalization/clipping
void	BaseMultiLayerUpdater.setStateViewArray(Layer layer, org.nd4j.linalg.api.ndarray.INDArray viewArray, boolean initialize)
void	BaseMultiLayerUpdater.update(Layer layer, Gradient gradient, int iteration, int batchSize)
static boolean	UpdaterUtils.updaterConfigurationsEquals(Layer layer1, String param1, Layer layer2, String param2)

Constructors in org.deeplearning4j.nn.updater with parameters of type Layer

Constructor and Description
LayerUpdater(Layer layer)
LayerUpdater(Layer layer, org.nd4j.linalg.api.ndarray.INDArray updaterState)

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

Fields in org.deeplearning4j.nn.updater.graph declared as Layer

Modifier and Type	Field and Description
protected Layer[]	ComputationGraphUpdater.orderedLayers

Methods in org.deeplearning4j.nn.updater.graph that return Layer

Modifier and Type	Method and Description
protected Layer[]	ComputationGraphUpdater.getOrderedLayers()

Uses of Layer in org.deeplearning4j.util

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

Modifier and Type	Method and Description
static org.nd4j.linalg.api.ndarray.INDArray	Dropout.applyDropConnect(Layer layer, String variable) Apply drop connect to the given variable