org.nd4j.linalg.api.ops.impl.controlflow

Class IfDerivative

java.lang.Object

org.nd4j.autodiff.functions.DifferentialFunction

org.nd4j.linalg.api.ops.impl.controlflow.If

org.nd4j.linalg.api.ops.impl.controlflow.IfDerivative

All Implemented Interfaces:

CustomOp

public class IfDerivative
extends If

Field Summary

Fields inherited from class org.nd4j.linalg.api.ops.impl.controlflow.If

blockName, dummyResult, falseBody, falseBodyExecution, falseBodyName, inputVars, loopBodyExecution, outputVars, predicate, predicateExecution, targetBoolean, trueBody, trueBodyExecuted, trueBodyName

Fields inherited from class org.nd4j.autodiff.functions.DifferentialFunction

dimensions, extraArgs, inPlace, sameDiff, scalarValue

Constructor Summary

Constructors

Constructor and Description
IfDerivative(If ifBlock)

Method Summary

Modifier and Type	Method and Description
List<int[]>	calculateOutputShape() Calculate the output shape for this op
List<SDVariable>	diff(List<SDVariable> i_v1) Perform automatic differentiation wrt the input variables
String	getBlockName()
SameDiff.SameDiffFunctionDefinition	getFalseBody()
SameDiff	getFalseBodyExecution()
String	getFalseBodyName()
SameDiff	getLoopBodyExecution()
SameDiff.SameDiffConditional	getPredicate()
SameDiff	getPredicateExecution()
Boolean	getTrueBodyExecuted()
String	opName() The name of the op

Methods inherited from class org.nd4j.linalg.api.ops.impl.controlflow.If

addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, doDiff, exectedTrueOrFalse, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, initFromOnnx, initFromTensorFlow, inputArguments, isInplaceCall, numIArguments, numInputArguments, numOutputArguments, numTArguments, onnxName, opHash, opType, outputArguments, outputVariables, populateInputsAndOutputsFromSameDiff, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, tArgs, tensorflowName, toString

Methods inherited from class org.nd4j.autodiff.functions.DifferentialFunction

arg, args, asProperties, attributeAdaptersForFunction, configFieldName, dup, equals, f, getValue, hashCode, hasPlaceHolderInputs, isConfigProperties, larg, mappingsForFunction, onnxNames, opNum, outputVariables, propertiesForFunction, rarg, resolvePropertiesFromSameDiffBeforeExecution, setInstanceId, setValueFor, tensorflowNames

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

IfDerivative

public IfDerivative(If ifBlock)

Method Detail

getTrueBodyExecuted

public Boolean getTrueBodyExecuted()

getFalseBody

public SameDiff.SameDiffFunctionDefinition getFalseBody()

getFalseBodyExecution

public SameDiff getFalseBodyExecution()

getBlockName

public String getBlockName()

getFalseBodyName

public String getFalseBodyName()

getLoopBodyExecution

public SameDiff getLoopBodyExecution()

getPredicate

public SameDiff.SameDiffConditional getPredicate()

getPredicateExecution

public SameDiff getPredicateExecution()

calculateOutputShape

public List<int[]> calculateOutputShape()

Description copied from class: DifferentialFunction

Calculate the output shape for this op

Specified by:

calculateOutputShape in interface CustomOp

Overrides:

calculateOutputShape in class If

Returns:

opName

public String opName()

Description copied from class: DifferentialFunction

The name of the op

Specified by:

opName in interface CustomOp

Overrides:

opName in class If

Returns:

diff

public List<SDVariable> diff(List<SDVariable> i_v1)

Description copied from class: DifferentialFunction

Perform automatic differentiation wrt the input variables

Overrides:

diff in class DifferentialFunction

Parameters:

i_v1 - the input variables

Returns:

the differentiated output wrt each input variable