Pooling3D.Pooling3DTypeDynamicCustomOp.DynamicCustomOpsBuilderaxis, bArguments, dArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, tArgumentsdimensions, extraArgs, inPlace, ownName, ownNameSetWithDefault, sameDiff, scalarValue| Constructor and Description |
|---|
Pooling3DDerivative(SameDiff sameDiff,
SDVariable[] inputs,
INDArray[] inputArrays,
INDArray[] outputs,
boolean inPlace,
Pooling3DConfig pooling3DConfig,
Pooling3D.Pooling3DType type) |
| 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.
|
String |
opName()
This method returns op opName as string
|
addArgs, configFieldName, getPoolingPrefix, iArgs, initFromTensorFlow, isConfigProperties, onnxName, propertiesForFunction, tensorflowNameaddBArgument, addDArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, bArgs, builder, calculateOutputShape, calculateOutputShape, clearArrays, dArgs, getBArgument, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, initFromOnnx, inputArguments, numBArguments, numDArguments, numIArguments, numInputArguments, numOutputArguments, numTArguments, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, setInputArgument, setInputArguments, setOutputArgument, tArgs, toString, wrapFilterNull, wrapOrNull, wrapOrNullarg, arg, argNames, args, attributeAdaptersForFunction, diff, dup, equals, getNumOutputs, getValue, hashCode, larg, mappingsForFunction, onnxNames, outputs, outputVariable, outputVariablesNames, rarg, replaceArg, setInstanceId, setPropertiesForFunction, setValueFor, tensorflowNamesclone, finalize, getClass, notify, notifyAll, wait, wait, waitisInplaceCallpublic Pooling3DDerivative(SameDiff sameDiff, SDVariable[] inputs, INDArray[] inputArrays, INDArray[] outputs, boolean inPlace, Pooling3DConfig pooling3DConfig, Pooling3D.Pooling3DType type)
public String opName()
DynamicCustomOpopName in interface CustomOpopName in class DynamicCustomOppublic List<SDVariable> doDiff(List<SDVariable> f1)
DifferentialFunctionpublic List<DataType> calculateOutputDataTypes(List<DataType> inputDataTypes)
DifferentialFunctionDifferentialFunction.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 Pooling3DinputDataTypes - The data types of the inputsCopyright © 2021. All rights reserved.