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

Packages that use BaseLayer

Package	Description
org.deeplearning4j.nn.conf.layers
org.deeplearning4j.nn.conf.layers.misc
org.deeplearning4j.nn.conf.layers.recurrent
org.deeplearning4j.nn.conf.layers.variational
org.deeplearning4j.nn.conf.ocnn
org.deeplearning4j.nn.conf.serde
org.deeplearning4j.nn.layers
org.deeplearning4j.nn.layers.recurrent

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

Subclasses of BaseLayer 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	AutoEncoder Autoencoder.
class	BaseOutputLayer
class	BasePretrainNetwork
class	BaseRecurrentLayer
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	Convolution3D 3D convolution layer configuration
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	DepthwiseConvolution2D 2D depth-wise convolution layer configuration.
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	EmbeddingSequenceLayer Embedding layer for sequences: feed-forward layer that expects fixed-length number (inputLength) of integers/indices per example as input, ranged from 0 to numClasses - 1.
class	FeedForwardLayer Created by jeffreytang on 7/21/15.
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	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	OutputLayer Output layer with different objective co-occurrences for different objectives.
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.

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

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

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

Subclasses of BaseLayer 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

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

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

Modifier and Type	Class and Description
class	SimpleRnn Simple RNN - aka "vanilla" RNN is the simplest type of recurrent neural network layer.

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

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

Modifier and Type	Class and Description
class	VariationalAutoencoder Variational Autoencoder layer

Uses of BaseLayer in org.deeplearning4j.nn.conf.ocnn

Subclasses of BaseLayer in org.deeplearning4j.nn.conf.ocnn

Modifier and Type	Class and Description
class	OCNNOutputLayer An implementation of one class neural networks from: https://arxiv.org/pdf/1802.06360.pdf The one class neural network approach is an extension of the standard output layer with a single set of weights, an activation function, and a bias to: 2 sets of weights, a learnable "r" parameter that is held static 1 traditional set of weights.

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

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

Modifier and Type	Method and Description
protected void	BaseNetConfigDeserializer.handleUpdaterBackwardCompatibility(BaseLayer layer, org.nd4j.shade.jackson.databind.node.ObjectNode on)

Uses of BaseLayer in org.deeplearning4j.nn.layers

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

Modifier and Type	Class and Description
class	BaseLayer<LayerConfT extends BaseLayer> A layer with parameters

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

Classes in org.deeplearning4j.nn.layers.recurrent with type parameters of type BaseLayer

Modifier and Type	Class and Description
class	BaseRecurrentLayer<LayerConfT extends BaseLayer>