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

Packages that use Layer

Package	Description
org.deeplearning4j.nn.api
org.deeplearning4j.nn.conf
org.deeplearning4j.nn.conf.layers
org.deeplearning4j.nn.conf.layers.convolutional
org.deeplearning4j.nn.conf.layers.misc
org.deeplearning4j.nn.conf.layers.objdetect
org.deeplearning4j.nn.conf.layers.recurrent
org.deeplearning4j.nn.conf.layers.samediff
org.deeplearning4j.nn.conf.layers.util
org.deeplearning4j.nn.conf.layers.variational
org.deeplearning4j.nn.conf.layers.wrapper
org.deeplearning4j.nn.conf.serde
org.deeplearning4j.nn.layers
org.deeplearning4j.nn.params
org.deeplearning4j.nn.transferlearning

Uses of Layer in org.deeplearning4j.nn.api

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

Modifier and Type	Method and Description
List<String>	ParamInitializer.biasKeys(Layer layer) Bias parameter keys given the layer configuration
boolean	ParamInitializer.isBiasParam(Layer layer, String key) Is the specified parameter a bias?
boolean	ParamInitializer.isWeightParam(Layer layer, String key) Is the specified parameter a weight?
int	ParamInitializer.numParams(Layer layer)
List<String>	ParamInitializer.paramKeys(Layer layer) Get a list of all parameter keys given the layer configuration
List<String>	ParamInitializer.weightKeys(Layer layer) Weight parameter keys given the layer configuration

Uses of Layer in org.deeplearning4j.nn.conf

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

Modifier and Type	Field and Description
protected Layer	NeuralNetConfiguration.layer
protected Layer	NeuralNetConfiguration.Builder.layer

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

Modifier and Type	Method and Description
ComputationGraphConfiguration.GraphBuilder	ComputationGraphConfiguration.GraphBuilder.addLayer(String layerName, Layer layer, InputPreProcessor preProcessor, String... layerInputs) Add a layer and an InputPreProcessor, with the specified name and specified inputs.
ComputationGraphConfiguration.GraphBuilder	ComputationGraphConfiguration.GraphBuilder.addLayer(String layerName, Layer layer, String... layerInputs) Add a layer, with no InputPreProcessor, with the specified name and specified inputs.
NeuralNetConfiguration.ListBuilder	NeuralNetConfiguration.ListBuilder.layer(int ind, Layer layer)
NeuralNetConfiguration.ListBuilder	NeuralNetConfiguration.ListBuilder.layer(Layer layer)
NeuralNetConfiguration.Builder	NeuralNetConfiguration.Builder.layer(Layer layer) Layer class.
ComputationGraphConfiguration.GraphBuilder	ComputationGraphConfiguration.GraphBuilder.layer(String layerName, Layer layer, InputPreProcessor preProcessor, String... layerInputs) Add a layer and an InputPreProcessor, with the specified name and specified inputs.
ComputationGraphConfiguration.GraphBuilder	ComputationGraphConfiguration.GraphBuilder.layer(String layerName, Layer layer, String... layerInputs) Add a layer, with no InputPreProcessor, with the specified name and specified inputs.
NeuralNetConfiguration.ListBuilder	NeuralNetConfiguration.Builder.list(Layer... layers) Create a ListBuilder (for creating a MultiLayerConfiguration) with the specified layers Usage:

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

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

Modifier and Type	Class and Description
class	AbstractLSTM LSTM recurrent net, based on Graves: Supervised Sequence Labelling with Recurrent Neural Networks http://www.cs.toronto.edu/~graves/phd.pdf
class	ActivationLayer
class	AutoEncoder Autoencoder.
class	BaseLayer A neural network layer.
class	BaseOutputLayer
class	BasePretrainNetwork
class	BaseRecurrentLayer
class	BaseUpsamplingLayer Upsampling base layer
class	BatchNormalization Batch normalization configuration
class	CenterLossOutputLayer Center loss is similar to triplet loss except that it enforces intraclass consistency and doesn't require feed forward of multiple examples.
class	CnnLossLayer Convolutional Neural Network Loss Layer. Handles calculation of gradients etc for various objective functions. NOTE: CnnLossLayer does not have any parameters.
class	Convolution1D 1D convolution layer
class	Convolution1DLayer 1D (temporal) convolutional layer.
class	Convolution2D 2D convolution layer
class	ConvolutionLayer
class	Deconvolution2D 2D deconvolution layer configuration Deconvolutions are also known as transpose convolutions or fractionally strided convolutions.
class	DenseLayer Dense layer: fully connected feed forward layer trainable by backprop.
class	DropoutLayer
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.
class	FeedForwardLayer Created by jeffreytang on 7/21/15.
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.
class	GravesBidirectionalLSTM Deprecated. use Bidirectional instead. With the Bidirectional layer wrapper you can make any recurrent layer bidirectional, in particular GravesLSTM. Note that this layer adds the output of both directions, which translates into "ADD" mode in Bidirectional. Usage: .layer(new Bidirectional(Bidirectional.Mode.ADD, new GravesLSTM.Builder()....build()))
class	GravesLSTM LSTM recurrent net, based on Graves: Supervised Sequence Labelling with Recurrent Neural Networks http://www.cs.toronto.edu/~graves/phd.pdf
class	LocalResponseNormalization Created by nyghtowl on 10/29/15.
class	LossLayer LossLayer is a flexible output "layer" that performs a loss function on an input without MLP logic.
class	LSTM LSTM recurrent net without peephole connections.
class	NoParamLayer
class	OutputLayer Output layer with different objective co-occurrences for different objectives.
class	Pooling1D 1D Pooling layer.
class	Pooling2D 2D Pooling layer.
class	RnnLossLayer Recurrent Neural Network Loss Layer. Handles calculation of gradients etc for various objective functions. NOTE: Unlike RnnOutputLayer this RnnLossLayer does not have any parameters - i.e., there is no time distributed dense component here.
class	RnnOutputLayer
class	SeparableConvolution2D 2D Separable convolution layer configuration.
class	SpaceToBatchLayer Space to batch utility layer configuration for convolutional input types.
class	SpaceToDepthLayer Space to depth utility layer configuration for convolutional input types.
class	Subsampling1DLayer 1D (temporal) subsampling layer.
class	SubsamplingLayer Subsampling layer also referred to as pooling in convolution neural nets Supports the following pooling types: MAX, AVG, SUM, PNORM, NONE
class	Upsampling1D Upsampling 1D layer
class	Upsampling2D Upsampling 2D layer
class	ZeroPadding1DLayer Zero padding 1D layer for convolutional neural networks.
class	ZeroPaddingLayer Zero padding layer for convolutional neural networks.

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

Modifier and Type	Method and Description
abstract <E extends Layer> E	Layer.Builder.build()

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

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

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

Modifier and Type	Method and Description
static void	LayerValidation.generalValidation(String layerName, Layer layer, IDropout iDropout, double l2, double l2Bias, double l1, double l1Bias, Distribution dist, List<LayerConstraint> allParamConstraints, List<LayerConstraint> weightConstraints, List<LayerConstraint> biasConstraints)
static void	LayerValidation.generalValidation(String layerName, Layer layer, IDropout iDropOut, Double l2, Double l2Bias, Double l1, Double l1Bias, Distribution dist, List<LayerConstraint> allParamConstraints, List<LayerConstraint> weightConstraints, List<LayerConstraint> biasConstraints)

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

Subclasses of Layer in org.deeplearning4j.nn.conf.layers.convolutional

Modifier and Type	Class and Description
class	Cropping2D Cropping layer for convolutional (2d) neural networks.

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

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

Modifier and Type	Class and Description
class	ElementWiseMultiplicationLayer Elementwise multiplication layer with weights: implements out = activationFn(input .* w + b) where: - w is a learnable weight vector of length nOut - ".*" is element-wise multiplication - b is a bias vector Note that the input and output sizes of the element-wise layer are the same for this layer
class	FrozenLayer Created by Alex on 10/07/2017.

Fields in org.deeplearning4j.nn.conf.layers.misc declared as Layer

Modifier and Type	Field and Description
protected Layer	FrozenLayer.layer

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

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

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

Modifier and Type	Method and Description
FrozenLayer.Builder	FrozenLayer.Builder.layer(Layer layer)

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

Constructor and Description
FrozenLayer(Layer layer)

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

Subclasses of Layer in org.deeplearning4j.nn.conf.layers.objdetect

Modifier and Type	Class and Description
class	Yolo2OutputLayer Output (loss) layer for YOLOv2 object detection model, based on the papers: YOLO9000: Better, Faster, Stronger - Redmon & Farhadi (2016) - https://arxiv.org/abs/1612.08242 and You Only Look Once: Unified, Real-Time Object Detection - Redmon et al.

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

Subclasses of Layer in org.deeplearning4j.nn.conf.layers.recurrent

Modifier and Type	Class and Description
class	Bidirectional Bidirectional is a "wrapper" layer: it wraps any uni-directional RNN layer to make it bidirectional. Note that multiple different modes are supported - these specify how the activations should be combined from the forward and backward RNN networks.
class	LastTimeStep LastTimeStep is a "wrapper" layer: it wraps any RNN layer, and extracts out the last time step during forward pass, and returns it as a row vector (per example).
class	SimpleRnn Simple RNN - aka "vanilla" RNN is the simplest type of recurrent neural network layer.

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

Modifier and Type	Method and Description
Layer	LastTimeStep.getUnderlying()

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

Modifier and Type	Method and Description
Bidirectional.Builder	Bidirectional.Builder.rnnLayer(Layer layer)

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

Constructor and Description
Bidirectional(Bidirectional.Mode mode, Layer layer) Create a Bidirectional wrapper for the specified layer
Bidirectional(Layer layer) Create a Bidirectional wrapper, with the default Mode (CONCAT) for the specified layer
LastTimeStep(Layer underlying)

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

Subclasses of Layer in org.deeplearning4j.nn.conf.layers.samediff

Modifier and Type	Class and Description
class	AbstractSameDiffLayer
class	BaseSameDiffLayer A base layer used for implementing Deeplearning4j layers using SameDiff.

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

Subclasses of Layer in org.deeplearning4j.nn.conf.layers.util

Modifier and Type	Class and Description
class	MaskLayer MaskLayer applies the mask array to the forward pass activations, and backward pass gradients, passing through this layer.
class	MaskZeroLayer

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

Constructor and Description
MaskZeroLayer(Layer underlying)

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

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

Modifier and Type	Class and Description
class	VariationalAutoencoder Variational Autoencoder layer

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

Subclasses of Layer in org.deeplearning4j.nn.conf.layers.wrapper

Modifier and Type	Class and Description
class	BaseWrapperLayer Base wrapper layer: the idea is to pass through all methods to the underlying layer, and selectively override them as required.

Fields in org.deeplearning4j.nn.conf.layers.wrapper declared as Layer

Modifier and Type	Field and Description
protected Layer	BaseWrapperLayer.underlying

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

Constructor and Description
BaseWrapperLayer(Layer underlying)

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

Methods in org.deeplearning4j.nn.conf.serde with parameters of type Layer

Modifier and Type	Method and Description
protected boolean	BaseNetConfigDeserializer.requiresDropoutFromLegacy(Layer[] layers)
protected boolean	BaseNetConfigDeserializer.requiresIUpdaterFromLegacy(Layer[] layers)

Uses of Layer in org.deeplearning4j.nn.layers

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

Modifier and Type	Class and Description
class	AbstractLayer<LayerConfT extends Layer> A layer with input and output, no parameters or gradients

Uses of Layer in org.deeplearning4j.nn.params

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

Modifier and Type	Method and Description
List<String>	BidirectionalParamInitializer.biasKeys(Layer layer)
List<String>	SeparableConvolutionParamInitializer.biasKeys(Layer layer)
List<String>	WrapperLayerParamInitializer.biasKeys(Layer layer)
List<String>	DefaultParamInitializer.biasKeys(Layer layer)
List<String>	LSTMParamInitializer.biasKeys(Layer layer)
List<String>	SimpleRnnParamInitializer.biasKeys(Layer layer)
List<String>	GravesLSTMParamInitializer.biasKeys(Layer layer)
List<String>	VariationalAutoencoderParamInitializer.biasKeys(Layer layer)
List<String>	EmptyParamInitializer.biasKeys(Layer layer)
List<String>	SameDiffParamInitializer.biasKeys(Layer layer)
List<String>	BatchNormalizationParamInitializer.biasKeys(Layer layer)
List<String>	FrozenLayerParamInitializer.biasKeys(Layer layer)
List<String>	GravesBidirectionalLSTMParamInitializer.biasKeys(Layer layer)
List<String>	ConvolutionParamInitializer.biasKeys(Layer layer)
protected boolean	DefaultParamInitializer.hasBias(Layer layer)
boolean	BidirectionalParamInitializer.isBiasParam(Layer layer, String key)
boolean	SeparableConvolutionParamInitializer.isBiasParam(Layer layer, String key)
boolean	WrapperLayerParamInitializer.isBiasParam(Layer layer, String key)
boolean	DefaultParamInitializer.isBiasParam(Layer layer, String key)
boolean	LSTMParamInitializer.isBiasParam(Layer layer, String key)
boolean	SimpleRnnParamInitializer.isBiasParam(Layer layer, String key)
boolean	GravesLSTMParamInitializer.isBiasParam(Layer layer, String key)
boolean	VariationalAutoencoderParamInitializer.isBiasParam(Layer layer, String key)
boolean	EmptyParamInitializer.isBiasParam(Layer layer, String key)
boolean	SameDiffParamInitializer.isBiasParam(Layer layer, String key)
boolean	BatchNormalizationParamInitializer.isBiasParam(Layer layer, String key)
boolean	FrozenLayerParamInitializer.isBiasParam(Layer layer, String key)
boolean	GravesBidirectionalLSTMParamInitializer.isBiasParam(Layer layer, String key)
boolean	ConvolutionParamInitializer.isBiasParam(Layer layer, String key)
boolean	BidirectionalParamInitializer.isWeightParam(Layer layer, String key)
boolean	SeparableConvolutionParamInitializer.isWeightParam(Layer layer, String key)
boolean	WrapperLayerParamInitializer.isWeightParam(Layer layer, String key)
boolean	DefaultParamInitializer.isWeightParam(Layer layer, String key)
boolean	LSTMParamInitializer.isWeightParam(Layer layer, String key)
boolean	SimpleRnnParamInitializer.isWeightParam(Layer layer, String key)
boolean	GravesLSTMParamInitializer.isWeightParam(Layer layer, String key)
boolean	VariationalAutoencoderParamInitializer.isWeightParam(Layer layer, String key)
boolean	EmptyParamInitializer.isWeightParam(Layer layer, String key)
boolean	SameDiffParamInitializer.isWeightParam(Layer layer, String key)
boolean	BatchNormalizationParamInitializer.isWeightParam(Layer layer, String key)
boolean	FrozenLayerParamInitializer.isWeightParam(Layer layer, String key)
boolean	GravesBidirectionalLSTMParamInitializer.isWeightParam(Layer layer, String key)
boolean	ConvolutionParamInitializer.isWeightParam(Layer layer, String key)
int	BidirectionalParamInitializer.numParams(Layer layer)
int	ElementWiseParamInitializer.numParams(Layer layer)
int	SeparableConvolutionParamInitializer.numParams(Layer l)
int	WrapperLayerParamInitializer.numParams(Layer layer)
int	DefaultParamInitializer.numParams(Layer l)
int	LSTMParamInitializer.numParams(Layer l)
int	SimpleRnnParamInitializer.numParams(Layer layer)
int	GravesLSTMParamInitializer.numParams(Layer l)
int	EmptyParamInitializer.numParams(Layer layer)
int	SameDiffParamInitializer.numParams(Layer layer)
int	BatchNormalizationParamInitializer.numParams(Layer l)
int	FrozenLayerParamInitializer.numParams(Layer layer)
int	GravesBidirectionalLSTMParamInitializer.numParams(Layer l)
int	ConvolutionParamInitializer.numParams(Layer l)
List<String>	BidirectionalParamInitializer.paramKeys(Layer layer)
List<String>	SeparableConvolutionParamInitializer.paramKeys(Layer layer)
List<String>	WrapperLayerParamInitializer.paramKeys(Layer layer)
List<String>	DefaultParamInitializer.paramKeys(Layer layer)
List<String>	LSTMParamInitializer.paramKeys(Layer layer)
List<String>	SimpleRnnParamInitializer.paramKeys(Layer layer)
List<String>	GravesLSTMParamInitializer.paramKeys(Layer layer)
List<String>	VariationalAutoencoderParamInitializer.paramKeys(Layer l)
List<String>	EmptyParamInitializer.paramKeys(Layer layer)
List<String>	SameDiffParamInitializer.paramKeys(Layer layer)
List<String>	BatchNormalizationParamInitializer.paramKeys(Layer layer)
List<String>	FrozenLayerParamInitializer.paramKeys(Layer layer)
List<String>	GravesBidirectionalLSTMParamInitializer.paramKeys(Layer layer)
List<String>	ConvolutionParamInitializer.paramKeys(Layer layer)
List<String>	BidirectionalParamInitializer.weightKeys(Layer layer)
List<String>	SeparableConvolutionParamInitializer.weightKeys(Layer layer)
List<String>	WrapperLayerParamInitializer.weightKeys(Layer layer)
List<String>	DefaultParamInitializer.weightKeys(Layer layer)
List<String>	LSTMParamInitializer.weightKeys(Layer layer)
List<String>	SimpleRnnParamInitializer.weightKeys(Layer layer)
List<String>	GravesLSTMParamInitializer.weightKeys(Layer layer)
List<String>	VariationalAutoencoderParamInitializer.weightKeys(Layer layer)
List<String>	EmptyParamInitializer.weightKeys(Layer layer)
List<String>	SameDiffParamInitializer.weightKeys(Layer layer)
List<String>	BatchNormalizationParamInitializer.weightKeys(Layer layer)
List<String>	FrozenLayerParamInitializer.weightKeys(Layer layer)
List<String>	GravesBidirectionalLSTMParamInitializer.weightKeys(Layer layer)
List<String>	ConvolutionParamInitializer.weightKeys(Layer layer)

Uses of Layer in org.deeplearning4j.nn.transferlearning

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

Modifier and Type	Method and Description
TransferLearning.Builder	TransferLearning.Builder.addLayer(Layer layer) Add layers to the net Required if layers are removed.
TransferLearning.GraphBuilder	TransferLearning.GraphBuilder.addLayer(String layerName, Layer layer, InputPreProcessor preProcessor, String... layerInputs) Add a layer with a specified preprocessor
TransferLearning.GraphBuilder	TransferLearning.GraphBuilder.addLayer(String layerName, Layer layer, String... layerInputs) Add a layer of the specified configuration to the computation graph