org.nd4j.linalg.api.ops.impl.accum

Class Variance

java.lang.Object

org.nd4j.autodiff.functions.DifferentialFunction

org.nd4j.linalg.api.ops.BaseOp

org.nd4j.linalg.api.ops.BaseAccumulation

org.nd4j.linalg.api.ops.impl.accum.Variance

All Implemented Interfaces:

Accumulation, Op

Direct Known Subclasses:

StandardDeviation

public class Variance
extends BaseAccumulation

Variance with bias correction. Bias can either be divided by n or adjusted with: (currentResult - (pow(bias, 2.0) / n())) / (n() - 1.0);

Author:

Adam Gibson

Nested Class Summary

Nested classes/interfaces inherited from interface org.nd4j.linalg.api.ops.Op

Op.Type

Field Summary

Fields

Modifier and Type	Field and Description
protected double	bias
protected boolean	biasCorrected
protected double	mean

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

finalResult, isComplex, keepDims, newFormat

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

extraArgs, extraArgz, n, numProcessed, passThrough, x, xVertexId, y, yVertexId, z, zVertexId

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

dimensions, inPlace, sameDiff, scalarValue

Constructor Summary

Constructors

Constructor and Description
Variance()
Variance(boolean biasCorrected)
Variance(INDArray x)
Variance(INDArray x, boolean biasCorrected)
Variance(INDArray x, INDArray y)
Variance(INDArray x, INDArray y, boolean biasCorrected)
Variance(INDArray x, INDArray y, INDArray z, long n)
Variance(INDArray x, INDArray y, INDArray z, long n, boolean biasCorrected)
Variance(INDArray x, INDArray y, long n)
Variance(INDArray x, INDArray y, long n, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, boolean biasCorrected)

Method Summary

Modifier and Type	Method and Description
List<SDVariable>	doDiff(List<SDVariable> i_v1) The actual implementation for automatic differentiation.
Op.Type	getOpType()
void	init(INDArray x, INDArray y, INDArray z, long n) Initialize the operation based on the parameters
boolean	isBiasCorrected()
boolean	isPassThrough() Returns whether the op should be executed or not (through the executioner)
INDArray	noOp() Returns the no op version of the input Basically when a reduce can't happen (eg: sum(0) on a row vector) you have a no op state for a given reduction.
String	onnxName() The opName of this function in onnx
String	opName() The name of the op
int	opNum() The number of the op (mainly for old legacy XYZ ops like Op)
void	setBiasCorrected(boolean biasCorrected)
String	tensorflowName() The opName of this function tensorflow

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

calculateOutputShape, getFinalResult, hasReductionIndices, initFromOnnx, initFromTensorFlow, isComplexAccumulation, isKeepDims, opType, setFinalResult, zeroDouble, zeroFloat, zeroHalf

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

equals, exec, exec, extraArgs, extraArgsBuff, extraArgsDataBuff, getOpType, hashCode, isExecSpecial, n, numProcessed, outputVariables, setN, setX, setY, setZ, toCustomOp, toString, x, y, z

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

arg, args, asProperties, attributeAdaptersForFunction, configFieldName, diff, dup, f, getValue, hasPlaceHolderInputs, isConfigProperties, larg, mappingsForFunction, onnxNames, outputVariables, 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.Op

exec, exec, extraArgs, extraArgsBuff, extraArgsDataBuff, isExecSpecial, n, numProcessed, setExtraArgs, setN, setX, setY, setZ, toCustomOp, x, y, z

Field Detail

mean

protected double mean

bias

protected double bias

biasCorrected

protected boolean biasCorrected

Constructor Detail

Variance

public Variance(SameDiff sameDiff,
                SDVariable i_v,
                int[] dimensions,
                boolean biasCorrected)

Variance

public Variance(SameDiff sameDiff,
                SDVariable i_v,
                SDVariable i_v2,
                int[] dimensions,
                boolean biasCorrected)

Variance

public Variance()

Variance

public Variance(boolean biasCorrected)

Variance

public Variance(INDArray x,
                INDArray y,
                INDArray z,
                long n)

Variance

public Variance(INDArray x,
                INDArray y,
                long n)

Variance

public Variance(INDArray x)

Variance

public Variance(INDArray x,
                INDArray y)

Variance

public Variance(INDArray x,
                INDArray y,
                INDArray z,
                long n,
                boolean biasCorrected)

Variance

public Variance(INDArray x,
                INDArray y,
                long n,
                boolean biasCorrected)

Variance

public Variance(INDArray x,
                boolean biasCorrected)

Variance

public Variance(INDArray x,
                INDArray y,
                boolean biasCorrected)

Method Detail

noOp

public INDArray noOp()

Description copied from interface: Accumulation

Returns the no op version of the input Basically when a reduce can't happen (eg: sum(0) on a row vector) you have a no op state for a given reduction. For most accumulations, this should return x but certain transformations should return say: the absolute value

Specified by:

noOp in interface Accumulation

Overrides:

noOp in class BaseAccumulation

Returns:

the no op version of the input

opNum

public int opNum()

Description copied from class: DifferentialFunction

The number of the op (mainly for old legacy XYZ ops like Op)

Specified by:

opNum in interface Op

Overrides:

opNum in class DifferentialFunction

Returns:

opName

public String opName()

Description copied from class: DifferentialFunction

The name of the op

Specified by:

opName in interface Op

Overrides:

opName in class DifferentialFunction

Returns:

the opName of this operation

init

public void init(INDArray x,
                 INDArray y,
                 INDArray z,
                 long n)

Description copied from interface: Op

Initialize the operation based on the parameters

Specified by:

init in interface Op

Overrides:

init in class BaseOp

Parameters:

x - the input

y - the pairwise transform ndarray

z - the resulting ndarray

n - the number of elements

isPassThrough

public boolean isPassThrough()

Description copied from interface: Op

Returns whether the op should be executed or not (through the executioner)

Specified by:

isPassThrough in interface Op

Overrides:

isPassThrough in class BaseOp

Returns:

true if the op is pass through false otherwise

isBiasCorrected

public boolean isBiasCorrected()

setBiasCorrected

public void setBiasCorrected(boolean biasCorrected)

doDiff

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

Description copied from class: DifferentialFunction

The actual implementation for automatic differentiation.

Specified by:

doDiff in class DifferentialFunction

Returns:

onnxName

public String onnxName()

Description copied from class: DifferentialFunction

The opName of this function in onnx

Specified by:

onnxName in class DifferentialFunction

Returns:

tensorflowName

public String tensorflowName()

Description copied from class: DifferentialFunction

The opName of this function tensorflow

Specified by:

tensorflowName in class DifferentialFunction

Returns:

getOpType

public Op.Type getOpType()