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

Class SoftmaxCrossEntropyLoss

java.lang.Object

org.nd4j.autodiff.functions.DifferentialFunction

org.nd4j.linalg.api.ops.DynamicCustomOp

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

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

All Implemented Interfaces:

CustomOp

public class SoftmaxCrossEntropyLoss
extends BaseLoss

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
static double	DEFAULT_LABEL_SMOOTHING

Fields inherited from class org.nd4j.linalg.api.ops.impl.loss.BaseLoss

lossReduce

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

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

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

dimensions, extraArgs, inPlace, ownName, ownNameSetWithDefault, sameDiff, scalarValue

Constructor Summary

Constructors

Constructor and Description
SoftmaxCrossEntropyLoss(INDArray labels, INDArray predictions, INDArray weights, LossReduce lossReduce, double labelSmoothing)
SoftmaxCrossEntropyLoss(SameDiff sameDiff, LossReduce lossReduce, SDVariable logits, SDVariable weights, SDVariable labels)
SoftmaxCrossEntropyLoss(SameDiff sameDiff, LossReduce lossReduce, SDVariable logits, SDVariable weights, SDVariable labels, double labelSmoothing)
SoftmaxCrossEntropyLoss(SameDiff sameDiff, SDVariable labels, SDVariable logits, SDVariable weights, LossReduce lossReduce, double labelSmoothing)

Method Summary

Modifier and Type	Method and Description
void	addArgs()
List<SDVariable>	doDiff(List<SDVariable> grad) The actual implementation for automatic differentiation.
void	initFromTensorFlow(NodeDef nodeDef, SameDiff initWith, Map<String,AttrValue> attributesForNode, GraphDef graph) Initialize the function from the given NodeDef
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

Methods inherited from class org.nd4j.linalg.api.ops.impl.loss.BaseLoss

calculateOutputDataTypes, getWeights, getWeights

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

addBArgument, addDArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, bArgs, builder, calculateOutputShape, calculateOutputShape, clearArrays, dArgs, getBArgument, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, 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, wrapOrNull

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

arg, arg, argNames, args, attributeAdaptersForFunction, configFieldName, diff, dup, equals, getNumOutputs, getValue, hashCode, isConfigProperties, larg, mappingsForFunction, onnxNames, outputs, outputVariable, outputVariablesNames, propertiesForFunction, rarg, replaceArg, 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

DEFAULT_LABEL_SMOOTHING

public static final double DEFAULT_LABEL_SMOOTHING

See Also:

Constant Field Values

Constructor Detail

SoftmaxCrossEntropyLoss

public SoftmaxCrossEntropyLoss(SameDiff sameDiff,
                               SDVariable labels,
                               SDVariable logits,
                               SDVariable weights,
                               LossReduce lossReduce,
                               double labelSmoothing)

SoftmaxCrossEntropyLoss

public SoftmaxCrossEntropyLoss(SameDiff sameDiff,
                               LossReduce lossReduce,
                               SDVariable logits,
                               SDVariable weights,
                               SDVariable labels,
                               double labelSmoothing)

SoftmaxCrossEntropyLoss

public SoftmaxCrossEntropyLoss(SameDiff sameDiff,
                               LossReduce lossReduce,
                               SDVariable logits,
                               SDVariable weights,
                               SDVariable labels)

SoftmaxCrossEntropyLoss

public SoftmaxCrossEntropyLoss(INDArray labels,
                               INDArray predictions,
                               INDArray weights,
                               LossReduce lossReduce,
                               double labelSmoothing)

Method Detail

addArgs

public void addArgs()

Overrides:

addArgs in class BaseLoss

initFromTensorFlow

public void initFromTensorFlow(NodeDef nodeDef,
                               SameDiff initWith,
                               Map<String,AttrValue> attributesForNode,
                               GraphDef graph)

Description copied from class: DifferentialFunction

Initialize the function from the given NodeDef

Overrides:

initFromTensorFlow in class DynamicCustomOp

opName

public String opName()

Description copied from class: DynamicCustomOp

This method returns op opName as string

Specified by:

opName in interface CustomOp

Specified by:

opName in class BaseLoss

Returns:

onnxName

public String onnxName()

Description copied from class: DifferentialFunction

The opName of this function in onnx

Overrides:

onnxName in class DynamicCustomOp

Returns:

tensorflowName

public String tensorflowName()

Description copied from class: DifferentialFunction

The opName of this function tensorflow

Overrides:

tensorflowName in class DynamicCustomOp

Returns:

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: