Uses of Interface
org.deeplearning4j.nn.conf.InputPreProcessor

Packages that use InputPreProcessor

Package	Description
org.deeplearning4j.nn.conf
org.deeplearning4j.nn.conf.graph
org.deeplearning4j.nn.conf.layers
org.deeplearning4j.nn.conf.preprocessor
org.deeplearning4j.nn.graph.vertex.impl

Uses of InputPreProcessor in org.deeplearning4j.nn.conf

Fields in org.deeplearning4j.nn.conf with type parameters of type InputPreProcessor

Modifier and Type	Field and Description
protected Map<Integer,InputPreProcessor>	MultiLayerConfiguration.inputPreProcessors
protected Map<Integer,InputPreProcessor>	MultiLayerConfiguration.Builder.inputPreProcessors
protected Map<String,InputPreProcessor>	ComputationGraphConfiguration.GraphBuilder.inputPreProcessors

Methods in org.deeplearning4j.nn.conf that return InputPreProcessor

Modifier and Type	Method and Description
InputPreProcessor	InputPreProcessor.clone()
InputPreProcessor	MultiLayerConfiguration.getInputPreProcess(int curr)

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

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.
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.inputPreProcessor(Integer layer, InputPreProcessor processor) Specify the processors.
ComputationGraphConfiguration.GraphBuilder	ComputationGraphConfiguration.GraphBuilder.inputPreProcessor(String layer, InputPreProcessor processor) Specify the processors for a given layer These are used at each layer for doing things like normalization and shaping of input. Note: preprocessors can also be defined using the ComputationGraphConfiguration.GraphBuilder.addLayer(String, Layer, InputPreProcessor, String...) method.

Method parameters in org.deeplearning4j.nn.conf with type arguments of type InputPreProcessor

Modifier and Type	Method and Description
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.inputPreProcessors(Map<Integer,InputPreProcessor> processors)

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

Constructors in org.deeplearning4j.nn.conf.graph with parameters of type InputPreProcessor

Constructor and Description
LayerVertex(NeuralNetConfiguration layerConf, InputPreProcessor preProcessor)
PreprocessorVertex(InputPreProcessor preProcessor)
PreprocessorVertex(InputPreProcessor preProcessor, InputType outputType) Deprecated. This constructor (and the "InputType override" functionality previously used is no longer necessary.

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

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

Modifier and Type	Method and Description
InputPreProcessor	SubsamplingLayer.getPreProcessorForInputType(InputType inputType)
InputPreProcessor	BatchNormalization.getPreProcessorForInputType(InputType inputType)
InputPreProcessor	ConvolutionLayer.getPreProcessorForInputType(InputType inputType)
abstract InputPreProcessor	Layer.getPreProcessorForInputType(InputType inputType) For the given type of input to this layer, what preprocessor (if any) is required? Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor
InputPreProcessor	BaseRecurrentLayer.getPreProcessorForInputType(InputType inputType)
InputPreProcessor	FeedForwardLayer.getPreProcessorForInputType(InputType inputType)
InputPreProcessor	LocalResponseNormalization.getPreProcessorForInputType(InputType inputType)
InputPreProcessor	RnnOutputLayer.getPreProcessorForInputType(InputType inputType)
InputPreProcessor	ActivationLayer.getPreProcessorForInputType(InputType inputType)
static InputPreProcessor	InputTypeUtil.getPreProcessorForInputTypeCnnLayers(InputType inputType, String layerName) Utility method for determining the appropriate preprocessor for CNN layers, such as ConvolutionLayer and SubsamplingLayer
static InputPreProcessor	InputTypeUtil.getPreprocessorForInputTypeRnnLayers(InputType inputType, String layerName)

Uses of InputPreProcessor in org.deeplearning4j.nn.conf.preprocessor

Classes in org.deeplearning4j.nn.conf.preprocessor that implement InputPreProcessor

Modifier and Type	Class and Description
class	BaseInputPreProcessor
class	BinomialSamplingPreProcessor Binomial sampling pre processor
class	CnnToFeedForwardPreProcessor A preprocessor to allow CNN and standard feed-forward network layers to be used together. For example, CNN -> Denselayer This does two things: (b) Reshapes 4d activations out of CNN layer, with shape [numExamples, numChannels, inputHeight, inputWidth]) into 2d activations (with shape [numExamples, inputHeight*inputWidth*numChannels]) for use in feed forward layer (a) Reshapes epsilons (weights*deltas) out of FeedFoward layer (which is 2D or 3D with shape [numExamples, inputHeight*inputWidth*numChannels]) into 4d epsilons (with shape [numExamples, numChannels, inputHeight, inputWidth]) suitable to feed into CNN layers. Note: numChannels is equivalent to depth or featureMaps referenced in different literature
class	CnnToRnnPreProcessor A preprocessor to allow CNN and RNN layers to be used together. For example, ConvolutionLayer -> GravesLSTM Functionally equivalent to combining CnnToFeedForwardPreProcessor + FeedForwardToRnnPreProcessor Specifically, this does two things: (a) Reshape 4d activations out of CNN layer, with shape [timeSeriesLength*miniBatchSize, numChannels, inputHeight, inputWidth]) into 3d (time series) activations (with shape [numExamples, inputHeight*inputWidth*numChannels, timeSeriesLength]) for use in RNN layers (b) Reshapes 3d epsilons (weights.*deltas) out of RNN layer (with shape [miniBatchSize,inputHeight*inputWidth*numChannels,timeSeriesLength]) into 4d epsilons with shape [miniBatchSize*timeSeriesLength, numChannels, inputHeight, inputWidth] suitable to feed into CNN layers.
class	ComposableInputPreProcessor Composable input pre processor
class	FeedForwardToCnnPreProcessor A preprocessor to allow CNN and standard feed-forward network layers to be used together. For example, DenseLayer -> CNN This does two things: (a) Reshapes activations out of FeedFoward layer (which is 2D or 3D with shape [numExamples, inputHeight*inputWidth*numChannels]) into 4d activations (with shape [numExamples, numChannels, inputHeight, inputWidth]) suitable to feed into CNN layers. (b) Reshapes 4d epsilons (weights*deltas) from CNN layer, with shape [numExamples, numChannels, inputHeight, inputWidth]) into 2d epsilons (with shape [numExamples, inputHeight*inputWidth*numChannels]) for use in feed forward layer Note: numChannels is equivalent to depth or featureMaps referenced in different literature
class	FeedForwardToRnnPreProcessor A preprocessor to allow RNN and feed-forward network layers to be used together. For example, DenseLayer -> GravesLSTM This does two things: (a) Reshapes activations out of FeedFoward layer (which is 2D with shape [miniBatchSize*timeSeriesLength,layerSize]) into 3d activations (with shape [miniBatchSize,layerSize,timeSeriesLength]) suitable to feed into RNN layers. (b) Reshapes 3d epsilons (weights*deltas from RNN layer, with shape [miniBatchSize,layerSize,timeSeriesLength]) into 2d epsilons (with shape [miniBatchSize*timeSeriesLength,layerSize]) for use in feed forward layer
class	ReshapePreProcessor Deprecated.
class	RnnToCnnPreProcessor A preprocessor to allow RNN and CNN layers to be used together For example, time series (video) input -> ConvolutionLayer, or conceivable GravesLSTM -> ConvolutionLayer Functionally equivalent to combining RnnToFeedForwardPreProcessor + FeedForwardToCnnPreProcessor Specifically, this does two things: (a) Reshape 3d activations out of RNN layer, with shape [miniBatchSize, numChannels*inputHeight*inputWidth, timeSeriesLength]) into 4d (CNN) activations (with shape [numExamples*timeSeriesLength, numChannels, inputWidth, inputHeight]) (b) Reshapes 4d epsilons (weights.*deltas) out of CNN layer (with shape [numExamples*timeSeriesLength, numChannels, inputHeight, inputWidth]) into 3d epsilons with shape [miniBatchSize, numChannels*inputHeight*inputWidth, timeSeriesLength] suitable to feed into CNN layers.
class	RnnToFeedForwardPreProcessor A preprocessor to allow RNN and feed-forward network layers to be used together. For example, GravesLSTM -> OutputLayer or GravesLSTM -> DenseLayer This does two things: (a) Reshapes activations out of RNN layer (which is 3D with shape [miniBatchSize,layerSize,timeSeriesLength]) into 2d activations (with shape [miniBatchSize*timeSeriesLength,layerSize]) suitable for use in feed-forward layers. (b) Reshapes 2d epsilons (weights*deltas from feed forward layer, with shape [miniBatchSize*timeSeriesLength,layerSize]) into 3d epsilons (with shape [miniBatchSize,layerSize,timeSeriesLength]) for use in RNN layer
class	UnitVarianceProcessor Unit variance operation
class	ZeroMeanAndUnitVariancePreProcessor Zero mean and unit variance operation
class	ZeroMeanPrePreProcessor Zero mean and unit variance operation

Constructors in org.deeplearning4j.nn.conf.preprocessor with parameters of type InputPreProcessor

Constructor and Description
ComposableInputPreProcessor(InputPreProcessor... inputPreProcessors)

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

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

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)
PreprocessorVertex(ComputationGraph graph, String name, int vertexIndex, InputPreProcessor preProcessor)
PreprocessorVertex(ComputationGraph graph, String name, int vertexIndex, VertexIndices[] inputVertices, VertexIndices[] outputVertices, InputPreProcessor preProcessor)