Class Variance
- java.lang.Object
-
- org.nd4j.autodiff.functions.DifferentialFunction
-
- org.nd4j.linalg.api.ops.BaseOp
-
- org.nd4j.linalg.api.ops.BaseReduceOp
-
- org.nd4j.linalg.api.ops.impl.summarystats.Variance
-
- Direct Known Subclasses:
StandardDeviation
public class Variance extends BaseReduceOp
-
-
Field Summary
Fields Modifier and Type Field Description protected double
bias
protected boolean
biasCorrected
protected double
mean
-
Fields inherited from class org.nd4j.linalg.api.ops.BaseReduceOp
dimensionVariable, isComplex, isEmptyReduce, keepDims
-
Fields inherited from class org.nd4j.linalg.api.ops.BaseOp
dimensionz, extraArgz, x, xVertexId, y, yVertexId, z, zVertexId
-
Fields inherited from class org.nd4j.autodiff.functions.DifferentialFunction
dimensions, extraArgs, inPlace, ownName, ownNameSetWithDefault, sameDiff, scalarValue
-
-
Constructor Summary
Constructors Constructor Description Variance()
Variance(boolean biasCorrected)
Variance(double mean)
Variance(double mean, double bias)
Variance(double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, double mean)
Variance(SameDiff sameDiff, double mean, double bias)
Variance(SameDiff sameDiff, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, boolean biasCorrected, boolean keepDims, int[] dimensions)
Variance(SameDiff sameDiff, SDVariable i_v, boolean keepDims, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, boolean keepDims, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, boolean keepDims, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, boolean keepDims, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, boolean keepDims, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, boolean keepDims, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable dimensions, boolean keepDims, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable dimensions, boolean keepDims, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable dimensions, boolean keepDims, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, boolean keepDims, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, boolean keepDims, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, boolean keepDims, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, double mean, double bias, boolean biasCorrected)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, SDVariable dimensions, double mean)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, SDVariable dimensions, double mean, double bias)
Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, SDVariable dimensions, double mean, double bias, boolean biasCorrected)
Variance(INDArray x, boolean biasCorrected, boolean keepDims, int... dimensions)
Variance(INDArray x, boolean keepDims, double mean, double bias, boolean biasCorrected, int... dimensions)
Variance(INDArray x, boolean keepDims, double mean, double bias, int... dimensions)
Variance(INDArray x, boolean keepDims, double mean, int... dimensions)
Variance(INDArray x, boolean biasCorrected, int... dimensions)
Variance(INDArray x, double mean, double bias, boolean biasCorrected, int... dimensions)
Variance(INDArray x, double mean, double bias, int... dimensions)
Variance(INDArray x, double mean, int... dimensions)
Variance(INDArray x, int... dimension)
Variance(INDArray x, INDArray z, boolean biasCorrected, boolean keepDims, int... dimensions)
Variance(INDArray x, INDArray z, boolean biasCorrected, int... dimensions)
Variance(INDArray x, INDArray y, double mean, double bias, boolean biasCorrected, int... dimensions)
Variance(INDArray x, INDArray y, double mean, double bias, int... dimensions)
Variance(INDArray x, INDArray y, double mean, int... dimensions)
Variance(INDArray x, INDArray y, INDArray z, boolean keepDims, int[] dimensions, double mean)
Variance(INDArray x, INDArray y, INDArray z, boolean keepDims, int[] dimensions, double mean, double bias)
Variance(INDArray x, INDArray y, INDArray z, boolean keepDims, int[] dimensions, double mean, double bias, boolean biasCorrected)
Variance(INDArray x, INDArray y, INDArray z, double mean, double bias, boolean biasCorrected, int... dimensions)
Variance(INDArray x, INDArray y, INDArray z, double mean, double bias, int... dimensions)
Variance(INDArray x, INDArray y, INDArray z, double mean, int... dimensions)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description List<DataType>
calculateOutputDataTypes(List<DataType> dataTypes)
Calculate the data types for the output arrays.List<LongShapeDescriptor>
calculateOutputShape()
Calculate the output shape for this opList<LongShapeDescriptor>
calculateOutputShape(OpContext oc)
List<SDVariable>
doDiff(List<SDVariable> grad)
The actual implementation for automatic differentiation.Op.Type
getOpType()
boolean
isBiasCorrected()
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 onnxString
opName()
The name of the opint
opNum()
The number of the op (mainly for old legacy XYZ ops likeOp
)Op.Type
opType()
The type of the opDataType
resultType()
This method returns datatype for result array wrt given inputsDataType
resultType(OpContext oc)
void
setBiasCorrected(boolean biasCorrected)
String
tensorflowName()
The opName of this function tensorflowboolean
validateDataTypes(OpContext oc)
-
Methods inherited from class org.nd4j.linalg.api.ops.BaseReduceOp
configureWithSameDiff, hasReductionIndices, initFromOnnx, initFromTensorFlow, isComplexAccumulation, isKeepDims, setDimensions, setPropertiesForFunction
-
Methods inherited from class org.nd4j.linalg.api.ops.BaseOp
clearArrays, computeVariables, defineDimensions, dimensions, equals, extraArgs, extraArgsBuff, extraArgsDataBuff, getFinalResult, getInputArgument, getNumOutputs, getOpType, hashCode, outputVariables, setX, setY, setZ, toCustomOp, toString, x, y, z
-
Methods inherited from class org.nd4j.autodiff.functions.DifferentialFunction
arg, arg, argNames, args, attributeAdaptersForFunction, configFieldName, diff, dup, getBooleanFromProperty, getDoubleValueFromProperty, getIntValueFromProperty, getLongValueFromProperty, getStringFromProperty, getValue, isConfigProperties, larg, mappingsForFunction, onnxNames, outputs, outputVariable, outputVariables, outputVariablesNames, propertiesForFunction, rarg, replaceArg, 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
clearArrays, extraArgs, extraArgsBuff, extraArgsDataBuff, setExtraArgs, setX, setY, setZ, toCustomOp, x, y, z
-
Methods inherited from interface org.nd4j.linalg.api.ops.ReduceOp
dimensions, getFinalResult
-
-
-
-
Constructor Detail
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, boolean keepDims, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, boolean keepDims, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, boolean keepDims, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable dimensions, boolean keepDims, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, double mean)
-
Variance
public Variance(double mean)
-
Variance
public Variance(INDArray x, INDArray y, INDArray z, boolean keepDims, int[] dimensions, double mean)
-
Variance
public Variance(INDArray x, double mean, int... dimensions)
-
Variance
public Variance(INDArray x, boolean keepDims, double mean, int... dimensions)
-
Variance
public Variance(SameDiff sameDiff, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, SDVariable dimensions, double mean)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, boolean keepDims, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, boolean keepDims, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, boolean keepDims, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable dimensions, boolean keepDims, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, double mean, double bias)
-
Variance
public Variance(double mean, double bias)
-
Variance
public Variance(INDArray x, INDArray y, INDArray z, boolean keepDims, int[] dimensions, double mean, double bias)
-
Variance
public Variance(INDArray x, double mean, double bias, int... dimensions)
-
Variance
public Variance(INDArray x, boolean keepDims, double mean, double bias, int... dimensions)
-
Variance
public Variance(INDArray x, INDArray y, INDArray z, double mean, double bias, int... dimensions)
-
Variance
public Variance(SameDiff sameDiff, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, SDVariable dimensions, double mean, double bias)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, boolean keepDims, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, boolean keepDims, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, int[] dimensions, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, int[] dimensions, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, boolean keepDims, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable dimensions, boolean keepDims, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(INDArray x, INDArray y, INDArray z, boolean keepDims, int[] dimensions, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(INDArray x, double mean, double bias, boolean biasCorrected, int... dimensions)
-
Variance
public Variance(INDArray x, boolean keepDims, double mean, double bias, boolean biasCorrected, int... dimensions)
-
Variance
public Variance(INDArray x, INDArray y, double mean, double bias, boolean biasCorrected, int... dimensions)
-
Variance
public Variance(INDArray x, INDArray y, INDArray z, double mean, double bias, boolean biasCorrected, int... dimensions)
-
Variance
public Variance(SameDiff sameDiff, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, SDVariable i_v2, SDVariable dimensions, double mean, double bias, boolean biasCorrected)
-
Variance
public Variance(SameDiff sameDiff, SDVariable i_v, boolean biasCorrected, boolean keepDims, int[] dimensions)
-
Variance
public Variance()
-
Variance
public Variance(boolean biasCorrected)
-
Variance
public Variance(INDArray x, int... dimension)
-
Variance
public Variance(INDArray x, boolean biasCorrected, boolean keepDims, int... dimensions)
-
Variance
public Variance(INDArray x, boolean biasCorrected, int... dimensions)
-
-
Method Detail
-
noOp
public INDArray noOp()
Description copied from interface:ReduceOp
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 interfaceReduceOp
- Overrides:
noOp
in classBaseReduceOp
- 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 likeOp
)- Specified by:
opNum
in interfaceOp
- Overrides:
opNum
in classDifferentialFunction
- Returns:
-
opName
public String opName()
Description copied from class:DifferentialFunction
The name of the op- Specified by:
opName
in interfaceOp
- Overrides:
opName
in classDifferentialFunction
- Returns:
- the opName of this operation
-
isBiasCorrected
public boolean isBiasCorrected()
-
setBiasCorrected
public void setBiasCorrected(boolean biasCorrected)
-
doDiff
public List<SDVariable> doDiff(List<SDVariable> grad)
Description copied from class:DifferentialFunction
The actual implementation for automatic differentiation.- Specified by:
doDiff
in classDifferentialFunction
- Returns:
-
onnxName
public String onnxName()
Description copied from class:DifferentialFunction
The opName of this function in onnx
-
tensorflowName
public String tensorflowName()
Description copied from class:DifferentialFunction
The opName of this function tensorflow- Overrides:
tensorflowName
in classBaseOp
- Returns:
-
getOpType
public Op.Type getOpType()
-
resultType
public DataType resultType()
Description copied from interface:ReduceOp
This method returns datatype for result array wrt given inputs- Returns:
-
validateDataTypes
public boolean validateDataTypes(OpContext oc)
-
calculateOutputShape
public List<LongShapeDescriptor> calculateOutputShape()
Description copied from class:DifferentialFunction
Calculate the output shape for this op- Specified by:
calculateOutputShape
in classBaseReduceOp
- Returns:
- List of output shape descriptors
-
calculateOutputShape
public List<LongShapeDescriptor> calculateOutputShape(OpContext oc)
- Overrides:
calculateOutputShape
in classDifferentialFunction
-
opType
public Op.Type opType()
Description copied from class:DifferentialFunction
The type of the op- Overrides:
opType
in classDifferentialFunction
- Returns:
-
calculateOutputDataTypes
public List<DataType> calculateOutputDataTypes(List<DataType> dataTypes)
Description copied from class:DifferentialFunction
Calculate the data types for the output arrays. Though datatypes can also be inferred fromDifferentialFunction.calculateOutputShape()
, this method differs in that it does not require the input arrays to be populated. This is important as it allows us to do greedy datatype inference for the entire net - even if arrays are not available.- Overrides:
calculateOutputDataTypes
in classDifferentialFunction
- Parameters:
dataTypes
- The data types of the inputs- Returns:
- The data types of the outputs
-
-