org.nd4j.linalg.api.ops.impl.transforms.comparison

Class Choose

java.lang.Object

org.nd4j.autodiff.functions.DifferentialFunction

org.nd4j.linalg.api.ops.DynamicCustomOp

org.nd4j.linalg.api.ops.impl.transforms.comparison.Choose

All Implemented Interfaces:

CustomOp

public class Choose
extends DynamicCustomOp

This op allows us to (based on the passed in condition) to return the element fulfilling the condition. In numpy, this is equivalent to the boolean indexing like: a[a > 2] which returns all elements in the array greater than 2 as a flat vector. This op interops with underlying libnd4j by leveraging the Condition.condtionNum()

Author:

Adam Gibson

Nested Class Summary

Nested classes/interfaces inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp

DynamicCustomOp.DynamicCustomOpsBuilder, DynamicCustomOp.SameDiffBuilder

Field Summary

Fields inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp

inplaceCall, outputVariables

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

dimensions, extraArgs, inPlace, sameDiff, scalarValue

Constructor Summary

Constructors

Constructor and Description
Choose()
Choose(INDArray[] inputs, Condition condition)
Choose(INDArray[] inputs, List<Integer> iArgs, List<Double> tArgs, Condition condition) Note that iArgs (integer arguments) and tArgs(double/float arguments) may end up being used under the following conditions: scalar operations (if a scalar is specified the you do not need to specify an ndarray) otherwise, if an ndarray is needed as a second input then put it in the inputs Usually, you only need 1 input (the equivalent of the array you're trying to do indexing on)
Choose(SameDiff sameDiff, SDVariable[] args, Condition condition)
Choose(String opName, INDArray[] inputs, Condition condition)
Choose(String opName, INDArray[] inputs, INDArray[] outputs, List<Double> tArguments, List<Integer> iArguments)
Choose(String opName, SameDiff sameDiff, SDVariable[] args, boolean inPlace)

Method Summary

Modifier and Type	Method and Description
String	opName() This method returns op opName as string

Methods inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp

addIArgument, addInputArgument, addOutputArgument, addTArgument, asProperties, assertValidForExecution, builder, calculateOutputShape, doDiff, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, initFromOnnx, initFromTensorFlow, inputArguments, numIArguments, numInputArguments, numOutputArguments, numTArguments, onnxName, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, populateInputsAndOutputsFromSameDiff, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, sameDiffBuilder, setInputArgument, setOutputArgument, tArgs, tensorflowName, toString, updateInputsFromSameDiff

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

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

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.nd4j.linalg.api.ops.CustomOp

isInplaceCall

Constructor Detail

Choose

public Choose(SameDiff sameDiff,
              SDVariable[] args,
              Condition condition)

Choose

public Choose(String opName,
              INDArray[] inputs,
              INDArray[] outputs,
              List<Double> tArguments,
              List<Integer> iArguments)

Choose

public Choose(String opName,
              INDArray[] inputs,
              Condition condition)

Choose

public Choose(INDArray[] inputs,
              Condition condition)

Parameters:

inputs -

condition -

Choose

public Choose(INDArray[] inputs,
              List<Integer> iArgs,
              List<Double> tArgs,
              Condition condition)

Note that iArgs (integer arguments) and tArgs(double/float arguments) may end up being used under the following conditions: scalar operations (if a scalar is specified the you do not need to specify an ndarray) otherwise, if an ndarray is needed as a second input then put it in the inputs Usually, you only need 1 input (the equivalent of the array you're trying to do indexing on)

Parameters:

inputs - the inputs in to the op

iArgs - the integer arguments as needed

tArgs - the arguments

condition - the condition to filter on

Choose

public Choose(String opName,
              SameDiff sameDiff,
              SDVariable[] args,
              boolean inPlace)

Choose

public Choose()

Method Detail

opName

public String opName()

Description copied from class: DynamicCustomOp

This method returns op opName as string

Specified by:

opName in interface CustomOp

Overrides:

opName in class DynamicCustomOp

Returns: