public class SliceBp extends DynamicCustomOp
DynamicCustomOp.DynamicCustomOpsBuilderaxis, bArguments, dArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, tArgumentsdimensions, extraArgs, inPlace, ownName, ownNameSetWithDefault, sameDiff, scalarValue| Constructor and Description |
|---|
SliceBp() |
SliceBp(SameDiff sameDiff,
@NonNull SDVariable input,
@NonNull SDVariable gradient,
@NonNull int[] begin,
@NonNull int[] size) |
SliceBp(SameDiff sameDiff,
@NonNull SDVariable input,
@NonNull SDVariable gradient,
@NonNull SDVariable begin,
@NonNull SDVariable size) |
| Modifier and Type | Method and Description |
|---|---|
void |
assertValidForExecution()
Asserts a valid state for execution,
otherwise throws an
ND4JIllegalStateException |
List<DataType> |
calculateOutputDataTypes(List<DataType> dataTypes)
Calculate the data types for the output arrays.
|
List<SDVariable> |
doDiff(List<SDVariable> i_v)
The actual implementation for automatic differentiation.
|
String |
opName()
This method returns op opName as string
|
addBArgument, addDArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addTArgument, bArgs, builder, calculateOutputShape, calculateOutputShape, clearArrays, dArgs, getBArgument, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, initFromOnnx, initFromTensorFlow, inputArguments, numBArguments, numDArguments, numIArguments, numInputArguments, numOutputArguments, numTArguments, onnxName, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, setInputArgument, setInputArguments, setOutputArgument, tArgs, tensorflowName, toString, wrapFilterNull, wrapOrNull, wrapOrNullarg, arg, argNames, args, attributeAdaptersForFunction, configFieldName, diff, dup, equals, getNumOutputs, getValue, hashCode, isConfigProperties, larg, mappingsForFunction, onnxNames, outputs, outputVariable, outputVariablesNames, propertiesForFunction, rarg, replaceArg, setInstanceId, setPropertiesForFunction, setValueFor, tensorflowNamesclone, finalize, getClass, notify, notifyAll, wait, wait, waitisInplaceCallpublic SliceBp()
public SliceBp(SameDiff sameDiff, @NonNull @NonNull SDVariable input, @NonNull @NonNull SDVariable gradient, @NonNull @NonNull int[] begin, @NonNull @NonNull int[] size)
public SliceBp(SameDiff sameDiff, @NonNull @NonNull SDVariable input, @NonNull @NonNull SDVariable gradient, @NonNull @NonNull SDVariable begin, @NonNull @NonNull SDVariable size)
public String opName()
DynamicCustomOpopName in interface CustomOpopName in class DynamicCustomOppublic void assertValidForExecution()
CustomOpND4JIllegalStateExceptionassertValidForExecution in interface CustomOpassertValidForExecution in class DynamicCustomOppublic List<SDVariable> doDiff(List<SDVariable> i_v)
DifferentialFunctiondoDiff in class DynamicCustomOppublic List<DataType> calculateOutputDataTypes(List<DataType> dataTypes)
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 DifferentialFunctiondataTypes - The data types of the inputsCopyright © 2021. All rights reserved.