Public

Get the Layer (if any). Returns null if #hasLayer() == false

getLayer

getVertexName

A representation of the vertices that are inputs to this vertex (inputs duing
forward pass)
Specific

getInputVertices

Get the array of inputs previously set for this GraphVertex

getInputs

This method clears inpjut for this vertex

clearVertex

doBackward

doForward

feedForwardMaskArrays

Get the epsilon/error (i.e., dL/dOutput) array previously set for this
GraphVertex

getEpsilon

A representation of the vertices that this vertex is connected to (outputs duing
forward pass) Speci

getOutputVertices

getVertexIndex

Whether the GraphVertex contains a Layer object or not

hasLayer

Whether the GraphVertex is an input vertex

isInputVertex

Whether the GraphVertex is an output vertex

isOutputVertex

See Layer#setBackpropGradientsViewArray(INDArray)

setBackpropGradientsViewArray

Set the errors (epsilon - aka dL/dActivation) for this GraphVertex

setEpsilon

setInput

setInputVertices

Only applies to layer vertices. Will throw exceptions on others. If applied to a
layer vertex it wil

setLayerAsFrozen

setOutputVertices

BufferedReader

Updating database using SQL prepared statement

 KeyStore is responsible for maintaining cryptographic keys and their owners. 
The type of the syste

java.security.KeyStore

Produces concatenated messages in language-neutral way. New code should probably
use java.util.Forma

java.text.MessageFormat

 Calendar is an abstract base class for converting between a Date object and a
set of integer fields

java.util.Calendar

A Set is a data structure which does not allow duplicate elements.

java.util.Set

 JarFile is used to read jar entries and their associated data from jar files.

java.util.jar.JarFile

Operations on java.lang.String that arenull safe.

 * IsEmpty/IsBlank - checks if a String contains 

org.apache.commons.lang.StringUtils

putExtra

getSystemService

setRequestProperty

/**
 * 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.
 *
 * @param inputs Input to network
 * @param training Whether training or not
 * @param storeLastForTBPTT set to true if used as part of truncated BPTT training
 * @return Activations for each layer (including input, as per feedforward() etc)
 */

//Do forward pass according to the topological ordering of the network

//This input: the 'vIdxInputNum'th input to vertex 'vIdx'

//Now, set the inputs for the next vertices:

//This (jth) connection from the output: is the 'inputNum'th input to vertex 'vIdx'

/**
     * Pretrain a specified layer with the given MultiDataSetIterator
     *
     * @param layerName       Layer name
     * @param iter Training data
     */

//Need to do partial forward pass. Simply folowing the topological ordering won't be efficient, as we might

// end up doing forward pass on layers we don't need to.

//However, we can start with the topological order, and prune out any layers we don't need to do

//Do we need to do forward pass on this GraphVertex?

//If it is input to any other layer we need, then yes. Otherwise: no

//At this point: have done all of the required forward pass stuff. Can now pretrain layer on current input

/**
     * PLEASE NEVER USE THIS METHOD IF YOU"RE NOT SURE WHAT YOU'll GET
     *
     * @param train
     * @param excludeOutputLayers
     * @param includeNonLayerVertexActivations
     * @param publicApi
     * @return
     */

// we're pushing input copies to outer workspace

// FIXME: we don't really want detach here

//When doing backprop (i.e., excludeOutputLayers = false), we don't need to do full forward pass through output layers too

// we only need to ensure the input to the output layers is set properly

// once again, pushing stuff out of this workspace

// FIXME: we don't really want detach here.

/**
 * 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. 
 *
 * @param 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]
 * @return 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).
 */

//As per MultiLayerNetwork.rnnTimeStep(): if inputs are all 2d, then outputs are all 2d

//Return 2d output with shape [miniBatchSize,nOut]

// instead of 3d output with shape [miniBatchSize,nOut,1]

How to use setInputmethodin org.deeplearning4j.nn.graph.vertex.GraphVertex

Best Java code snippets using org.deeplearning4j.nn.graph.vertex.GraphVertex.setInput (Showing top 4 results out of 315)

How to use
setInput
method
in
org.deeplearning4j.nn.graph.vertex.GraphVertex