public class GaussianDistribution extends BaseRandomOp
dataType, shape
dimensionz, extraArgz, x, xVertexId, y, yVertexId, z, zVertexId
dimensions, extraArgs, inPlace, sameDiff, scalarValue
Constructor and Description |
---|
GaussianDistribution() |
GaussianDistribution(double mean,
double stddev,
DataType datatype,
long... shape) |
GaussianDistribution(@NonNull INDArray z)
This op fills Z with random values within -1.0..0..1.0
|
GaussianDistribution(@NonNull INDArray z,
double stddev)
This op fills Z with random values within stddev..0..stddev
|
GaussianDistribution(@NonNull INDArray z,
double mean,
double stddev)
This op fills Z with random values within stddev..mean..stddev boundaries
|
GaussianDistribution(@NonNull INDArray z,
@NonNull INDArray means,
double stddev) |
GaussianDistribution(SameDiff sd,
double mean,
double stddev,
DataType dataType,
long[] shape) |
GaussianDistribution(SameDiff sd,
double mean,
double stddev,
long[] shape) |
Modifier and Type | Method and Description |
---|---|
List<DataType> |
calculateOutputDataTypes(List<DataType> inputDataTypes)
Calculate the data types for the output arrays.
|
List<SDVariable> |
doDiff(List<SDVariable> f1)
The actual implementation for automatic differentiation.
|
boolean |
isTripleArgRngOp() |
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 |
setZ(INDArray z)
set z (the solution ndarray)
|
String |
tensorflowName()
The opName of this function tensorflow
|
calculateOutputShape, calculateOutputShape, isInPlace, opType
clearArrays, defineDimensions, dimensions, equals, extraArgs, extraArgsBuff, extraArgsDataBuff, getFinalResult, getInputArgument, getNumOutputs, getOpType, hashCode, initFromOnnx, initFromTensorFlow, outputVariables, setX, setY, toCustomOp, toString, x, y, z
arg, arg, argNames, args, attributeAdaptersForFunction, configFieldName, diff, dup, getValue, isConfigProperties, larg, mappingsForFunction, onnxNames, outputs, outputVariable, outputVariables, outputVariablesNames, propertiesForFunction, rarg, replaceArg, setInstanceId, setPropertiesForFunction, setValueFor, tensorflowNames
clone, finalize, getClass, notify, notifyAll, wait, wait, wait
clearArrays, extraArgs, extraArgsBuff, extraArgsDataBuff, setExtraArgs, setX, setY, toCustomOp, x, y, z
public GaussianDistribution(SameDiff sd, double mean, double stddev, long[] shape)
public GaussianDistribution(SameDiff sd, double mean, double stddev, DataType dataType, long[] shape)
public GaussianDistribution()
public GaussianDistribution(double mean, double stddev, DataType datatype, long... shape)
public GaussianDistribution(@NonNull @NonNull INDArray z, double mean, double stddev)
z
- mean
- stddev
- public GaussianDistribution(@NonNull @NonNull INDArray z, @NonNull @NonNull INDArray means, double stddev)
public GaussianDistribution(@NonNull @NonNull INDArray z)
z
- public GaussianDistribution(@NonNull @NonNull INDArray z, double stddev)
z
- public int opNum()
DifferentialFunction
Op
)opNum
in interface Op
opNum
in class DifferentialFunction
public String opName()
DifferentialFunction
opName
in interface Op
opName
in class DifferentialFunction
public String onnxName()
DifferentialFunction
public String tensorflowName()
DifferentialFunction
tensorflowName
in class BaseOp
public void setZ(INDArray z)
Op
public List<SDVariable> doDiff(List<SDVariable> f1)
DifferentialFunction
doDiff
in class DifferentialFunction
public List<DataType> calculateOutputDataTypes(List<DataType> inputDataTypes)
DifferentialFunction
DifferentialFunction.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.calculateOutputDataTypes
in class BaseRandomOp
inputDataTypes
- The data types of the inputspublic boolean isTripleArgRngOp()
isTripleArgRngOp
in class BaseRandomOp
Copyright © 2020. All rights reserved.