public abstract class BaseLoss extends DynamicCustomOp
DynamicCustomOp.DynamicCustomOpsBuilder
Modifier and Type | Field and Description |
---|---|
protected LossReduce |
lossReduce |
axis, bArguments, dArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, tArguments
dimensions, extraArgs, inPlace, sameDiff, scalarValue
Modifier | Constructor and Description |
---|---|
protected |
BaseLoss() |
|
BaseLoss(@NonNull LossReduce lossReduce,
@NonNull INDArray predictions,
INDArray weights,
@NonNull INDArray labels) |
|
BaseLoss(@NonNull SameDiff sameDiff,
@NonNull LossReduce lossReduce,
@NonNull SDVariable predictions,
SDVariable weights,
@NonNull SDVariable labels) |
Modifier and Type | Method and Description |
---|---|
protected void |
addArgs() |
List<DataType> |
calculateOutputDataTypes(List<DataType> inputDataTypes)
Calculate the data types for the output arrays.
|
protected static INDArray |
getWeights(INDArray weights,
INDArray predictions) |
protected static SDVariable |
getWeights(SameDiff sd,
SDVariable weights,
SDVariable predictions) |
abstract String |
opName()
This method returns op opName as string
|
addBArgument, addDArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, bArgs, builder, calculateOutputShape, calculateOutputShape, clearArrays, dArgs, doDiff, 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, wrapOrNull
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
clone, finalize, getClass, notify, notifyAll, wait, wait, wait
isInplaceCall
protected LossReduce lossReduce
public BaseLoss(@NonNull @NonNull SameDiff sameDiff, @NonNull @NonNull LossReduce lossReduce, @NonNull @NonNull SDVariable predictions, SDVariable weights, @NonNull @NonNull SDVariable labels)
public BaseLoss(@NonNull @NonNull LossReduce lossReduce, @NonNull @NonNull INDArray predictions, INDArray weights, @NonNull @NonNull INDArray labels)
protected BaseLoss()
protected static SDVariable getWeights(SameDiff sd, SDVariable weights, SDVariable predictions)
protected void addArgs()
public abstract String opName()
DynamicCustomOp
opName
in interface CustomOp
opName
in class DynamicCustomOp
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 DifferentialFunction
inputDataTypes
- The data types of the inputsCopyright © 2020. All rights reserved.