org.nd4j.linalg.api.ops.impl.layers

Class Linear

java.lang.Object

org.nd4j.autodiff.functions.DifferentialFunction

org.nd4j.linalg.api.ops.DynamicCustomOp

org.nd4j.linalg.api.ops.BaseModule

org.nd4j.linalg.api.ops.impl.layers.Linear

All Implemented Interfaces:

CustomOp, Module

public class Linear
extends BaseModule

Linear: a * bT

Author:

Adam Gibson

Nested Class Summary

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

DynamicCustomOp.DynamicCustomOpsBuilder, DynamicCustomOp.SameDiffBuilder

Field Summary

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

inplaceCall, outputVariables

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

dimensions, extraArgs, inPlace, sameDiff, scalarValue

Constructor Summary

Constructors

Constructor and Description
Linear(int nIn, int nOut, WeightInitScheme weightInitScheme, WeightInitScheme biasWeightInitScheme)
Linear(SameDiff sameDiff, int nIn, int nOut, WeightInitScheme weightInitScheme, WeightInitScheme biasWeightInitScheme)

Method Summary

Modifier and Type	Method and Description
List<int[]>	calculateOutputShape() Calculate the output shape for this op
List<SDVariable>	doDiff(List<SDVariable> f1) The actual implementation for automatic differentiation.
void	exec(INDArray... inputs)
void	execSameDiff(SDVariable... input)
void	initFromOnnx(OnnxProto3.NodeProto node, SameDiff initWith, Map<String,OnnxProto3.AttributeProto> attributesForNode, OnnxProto3.GraphProto graph) Iniitialize the function from the given OnnxProto3.NodeProto
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.BaseModule

addModule, subModules

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

addIArgument, addInputArgument, addOutputArgument, addTArgument, asProperties, assertValidForExecution, builder, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, inputArguments, numIArguments, numInputArguments, numOutputArguments, numTArguments, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, populateInputsAndOutputsFromSameDiff, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, sameDiffBuilder, setInputArgument, setOutputArgument, tArgs, toString, updateInputsFromSameDiff

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

arg, args, attributeAdaptersForFunction, configFieldName, diff, dup, equals, f, getValue, hashCode, hasPlaceHolderInputs, isConfigProperties, larg, mappingsForFunction, onnxNames, propertiesForFunction, rarg, resolvePropertiesFromSameDiffBeforeExecution, setInstanceId, 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

addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, inputArguments, isInplaceCall, numIArguments, numInputArguments, numOutputArguments, numTArguments, opHash, outputArguments, populateInputsAndOutputsFromSameDiff, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, tArgs

Constructor Detail

Linear

public Linear(int nIn,
              int nOut,
              WeightInitScheme weightInitScheme,
              WeightInitScheme biasWeightInitScheme)

Linear

public Linear(SameDiff sameDiff,
              int nIn,
              int nOut,
              WeightInitScheme weightInitScheme,
              WeightInitScheme biasWeightInitScheme)

Method Detail

opName

public 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:

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

initFromOnnx

public void initFromOnnx(OnnxProto3.NodeProto node,
                         SameDiff initWith,
                         Map<String,OnnxProto3.AttributeProto> attributesForNode,
                         OnnxProto3.GraphProto graph)

Description copied from class: DifferentialFunction

Iniitialize the function from the given OnnxProto3.NodeProto

Overrides:

initFromOnnx in class DynamicCustomOp

doDiff

public List<SDVariable> doDiff(List<SDVariable> f1)

Description copied from class: DifferentialFunction

The actual implementation for automatic differentiation.

Overrides:

doDiff in class DynamicCustomOp

Returns:

calculateOutputShape

public List<int[]> calculateOutputShape()

Description copied from class: DifferentialFunction

Calculate the output shape for this op

Specified by:

calculateOutputShape in interface CustomOp

Overrides:

calculateOutputShape in class DynamicCustomOp

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:

exec

public void exec(INDArray... inputs)

execSameDiff

public void execSameDiff(SDVariable... input)