org.nd4j.linalg.api.ops.impl.loss.bp

Class BaseLossBp

java.lang.Object

org.nd4j.autodiff.functions.DifferentialFunction

org.nd4j.linalg.api.ops.DynamicCustomOp

org.nd4j.linalg.api.ops.impl.loss.bp.BaseLossBp

All Implemented Interfaces:

CustomOp

Direct Known Subclasses:

AbsoluteDifferenceLossBp, CosineDistanceLossBp, HingeLossBp, HuberLossBp, LogLossBp, LogPoissonLossBp, MeanPairwiseSquaredErrorLossBp, MeanSquaredErrorLossBp, SigmoidCrossEntropyLossBp, SoftmaxCrossEntropyLossBp

public abstract class BaseLossBp
extends DynamicCustomOp

Nested Class Summary

Nested classes/interfaces inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp

DynamicCustomOp.DynamicCustomOpsBuilder

Field Summary

Fields

Modifier and Type	Field and Description
protected LossReduce	lossReduce

Fields inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp

axis, bArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, tArguments

Fields inherited from class org.nd4j.autodiff.functions.DifferentialFunction

dimensions, extraArgs, inPlace, sameDiff, scalarValue

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	BaseLossBp()
	BaseLossBp(SameDiff sameDiff, LossReduce lossReduce, SDVariable predictions, SDVariable weights, SDVariable labels)

Method Summary

Modifier and Type	Method and Description
protected void	addArgs()
List<DataType>	calculateOutputDataTypes(List<DataType> inputDataTypes) Calculate the data types for the output arrays.
List<SDVariable>	doDiff(List<SDVariable> grad) The actual implementation for automatic differentiation.
int	getNumOutputs()
abstract String	opName() This method returns op opName as string

Methods inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp

addBArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, bArgs, builder, calculateOutputShape, getBArgument, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, initFromOnnx, initFromTensorFlow, inputArguments, numBArguments, numIArguments, numInputArguments, numOutputArguments, numTArguments, onnxName, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, setInputArgument, setInputArguments, setOutputArgument, tArgs, tensorflowName, toString, wrapFilterNull, wrapOrNull

Methods inherited from class org.nd4j.autodiff.functions.DifferentialFunction

arg, arg, argNames, args, attributeAdaptersForFunction, configFieldName, diff, dup, equals, f, getValue, hashCode, isConfigProperties, larg, mappingsForFunction, onnxNames, outputVariable, outputVariablesNames, propertiesForFunction, rarg, replaceArg, resolvePropertiesFromSameDiffBeforeExecution, setInstanceId, setPropertiesForFunction, 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.CustomOp

isInplaceCall

Field Detail

lossReduce

protected LossReduce lossReduce

Constructor Detail

BaseLossBp

public BaseLossBp(@NonNull
                  SameDiff sameDiff,
                  @NonNull
                  LossReduce lossReduce,
                  @NonNull
                  SDVariable predictions,
                  @NonNull
                  SDVariable weights,
                  @NonNull
                  SDVariable labels)

BaseLossBp

protected BaseLossBp()

Method Detail

addArgs

protected void addArgs()

opName

public abstract String opName()

Description copied from class: DynamicCustomOp

This method returns op opName as string

Specified by:

opName in interface CustomOp

Overrides:

opName in class DynamicCustomOp

Returns:

getNumOutputs

public int getNumOutputs()

Overrides:

getNumOutputs in class DifferentialFunction

calculateOutputDataTypes

public List<DataType> calculateOutputDataTypes(List<DataType> inputDataTypes)

Description copied from class: DifferentialFunction

Calculate the data types for the output arrays. Though datatypes can also be inferred from 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.

Overrides:

calculateOutputDataTypes in class DifferentialFunction

Parameters:

inputDataTypes - The data types of the inputs

Returns:

The data types of the outputs

doDiff

public List<SDVariable> doDiff(List<SDVariable> grad)

Description copied from class: DifferentialFunction

The actual implementation for automatic differentiation.

Overrides:

doDiff in class DynamicCustomOp

Returns: