DynamicCustomOp.DynamicCustomOpsBuilder
axis, bArguments, dArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, tArguments
dimensions, extraArgs, inPlace, sameDiff, scalarValue
Constructor and Description |
---|
SConv2DDerivative() |
SConv2DDerivative(SameDiff sameDiff,
SDVariable[] inputFunctions,
Conv2DConfig conv2DConfig) |
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.
|
int |
getNumOutputs() |
String |
onnxName()
The opName of this function in onnx
|
String |
opName()
This method returns op opName as string
|
String |
tensorflowName()
The opName of this function tensorflow
|
String[] |
tensorflowNames()
The opName of this function tensorflow
|
configFieldName, iArgs, isConfigProperties
addArgs, attributeAdaptersForFunction, getValue, initConfig, initFromOnnx, initFromTensorFlow, mappingsForFunction, propertiesForFunction
addBArgument, addDArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, bArgs, builder, calculateOutputShape, calculateOutputShape, clearArrays, dArgs, getBArgument, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, inputArguments, numBArguments, numDArguments, numIArguments, numInputArguments, numOutputArguments, numTArguments, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, setInputArgument, setInputArguments, setOutputArgument, tArgs, toString, wrapFilterNull, wrapOrNull, wrapOrNull
arg, arg, argNames, args, diff, dup, equals, hashCode, larg, onnxNames, outputs, outputVariable, outputVariablesNames, rarg, replaceArg, setInstanceId, setPropertiesForFunction, setValueFor
clone, finalize, getClass, notify, notifyAll, wait, wait, wait
isInplaceCall
public SConv2DDerivative(SameDiff sameDiff, SDVariable[] inputFunctions, Conv2DConfig conv2DConfig)
public SConv2DDerivative()
public String opName()
DynamicCustomOp
public String[] tensorflowNames()
DifferentialFunction
tensorflowNames
in class SConv2D
public String onnxName()
DifferentialFunction
public String tensorflowName()
DifferentialFunction
tensorflowName
in class SConv2D
public List<SDVariable> doDiff(List<SDVariable> f1)
DifferentialFunction
public int getNumOutputs()
getNumOutputs
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 SConv2D
inputDataTypes
- The data types of the inputsCopyright © 2020. All rights reserved.