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

Class Conv2D

java.lang.Object

org.nd4j.autodiff.functions.DifferentialFunction

org.nd4j.linalg.api.ops.DynamicCustomOp

org.nd4j.linalg.api.ops.impl.layers.convolution.Conv2D

All Implemented Interfaces:

CustomOp

Direct Known Subclasses:

Conv2DDerivative, SConv2D

public class Conv2D
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 Conv2DConfig	config

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
Conv2D(INDArray[] inputs, INDArray[] outputs, Conv2DConfig config)
Conv2D(INDArray layerInput, INDArray weights, INDArray bias, Conv2DConfig config)
Conv2D(@NonNull INDArray input, @NonNull INDArray weights, INDArray bias, INDArray output, @NonNull Conv2DConfig config)
Conv2D(SameDiff sameDiff, SDVariable[] inputFunctions, Conv2DConfig config)
Conv2D(@NonNull SameDiff sameDiff, @NonNull SDVariable input, @NonNull SDVariable weights, SDVariable bias, @NonNull Conv2DConfig conv2DConfig)

Method Summary

Modifier and Type	Method and Description
protected void	addArgs()
Map<String,Map<String,AttributeAdapter>>	attributeAdaptersForFunction() Returns the AttributeAdapter s for each of the possible ops for import (typically tensorflow and onnx) See AttributeAdapter for more information on what the adapter does.
List<DataType>	calculateOutputDataTypes(List<DataType> inputDataTypes) Calculate the data types for the output arrays.
String	configFieldName() Returns the name of the field to be used for looking up field names.
List<SDVariable>	doDiff(List<SDVariable> f1) The actual implementation for automatic differentiation.
Object	getValue(Field property) Get the value for a given property for this function
long[]	iArgs()
protected void	initConfig(Conv2DConfig config)
void	initFromOnnx(Onnx.NodeProto node, SameDiff initWith, Map<String,Onnx.AttributeProto> attributesForNode, Onnx.GraphProto graph) Iniitialize the function from the given Onnx.NodeProto
void	initFromTensorFlow(NodeDef nodeDef, SameDiff initWith, Map<String,AttrValue> attributesForNode, GraphDef graph) Initialize the function from the given NodeDef
boolean	isConfigProperties() Returns true if the fields for this class should be looked up from a configuration class.
Map<String,Map<String,PropertyMapping>>	mappingsForFunction() Returns the mappings for a given function ( for tensorflow and onnx import mapping properties of this function).
String	onnxName() The opName of this function in onnx
String	opName() This method returns op opName as string
Map<String,Object>	propertiesForFunction() Returns the properties for a given function
String	tensorflowName() The opName of this function tensorflow
String[]	tensorflowNames() The opName of this function tensorflow

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, 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, diff, dup, equals, getNumOutputs, hashCode, larg, onnxNames, outputs, outputVariable, outputVariablesNames, rarg, replaceArg, setInstanceId, setPropertiesForFunction, setValueFor

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

config

protected Conv2DConfig config

Constructor Detail

Conv2D

public Conv2D(@NonNull
              @NonNull SameDiff sameDiff,
              @NonNull
              @NonNull SDVariable input,
              @NonNull
              @NonNull SDVariable weights,
              SDVariable bias,
              @NonNull
              @NonNull Conv2DConfig conv2DConfig)

Conv2D

public Conv2D(SameDiff sameDiff,
              SDVariable[] inputFunctions,
              Conv2DConfig config)

Conv2D

public Conv2D(INDArray[] inputs,
              INDArray[] outputs,
              Conv2DConfig config)

Conv2D

public Conv2D(@NonNull
              @NonNull INDArray input,
              @NonNull
              @NonNull INDArray weights,
              INDArray bias,
              INDArray output,
              @NonNull
              @NonNull Conv2DConfig config)

Conv2D

public Conv2D(INDArray layerInput,
              INDArray weights,
              INDArray bias,
              Conv2DConfig config)

Method Detail

initConfig

protected void initConfig(Conv2DConfig config)

addArgs

protected void addArgs()

iArgs

public long[] iArgs()

Specified by:

iArgs in interface CustomOp

Overrides:

iArgs in class DynamicCustomOp

getValue

public Object getValue(Field property)

Description copied from class: DifferentialFunction

Get the value for a given property for this function

Overrides:

getValue in class DifferentialFunction

Parameters:

property - the property to get

Returns:

the value for the function if it exists

propertiesForFunction

public Map<String,Object> propertiesForFunction()

Description copied from class: DifferentialFunction

Returns the properties for a given function

Overrides:

propertiesForFunction in class DifferentialFunction

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

isConfigProperties

public boolean isConfigProperties()

Description copied from class: DifferentialFunction

Returns true if the fields for this class should be looked up from a configuration class.

Overrides:

isConfigProperties in class DifferentialFunction

Returns:

configFieldName

public String configFieldName()

Description copied from class: DifferentialFunction

Returns the name of the field to be used for looking up field names. This should be used in conjunction with DifferentialFunction.isConfigProperties() to facilitate mapping fields for model import.

Overrides:

configFieldName in class DifferentialFunction

Returns:

initFromOnnx

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

Description copied from class: DifferentialFunction

Iniitialize the function from the given Onnx.NodeProto

Overrides:

initFromOnnx in class DynamicCustomOp

attributeAdaptersForFunction

public Map<String,Map<String,AttributeAdapter>> attributeAdaptersForFunction()

Description copied from class: DifferentialFunction

Returns the AttributeAdapter s for each of the possible ops for import (typically tensorflow and onnx) See AttributeAdapter for more information on what the adapter does. Similar to DifferentialFunction.mappingsForFunction(), the returned map contains a AttributeAdapter for each field name when one is present. (It is optional for one to exist)_

Overrides:

attributeAdaptersForFunction in class DifferentialFunction

Returns:

mappingsForFunction

public Map<String,Map<String,PropertyMapping>> mappingsForFunction()

Description copied from class: DifferentialFunction

Returns the mappings for a given function ( for tensorflow and onnx import mapping properties of this function). The mapping is indexed by field name. If the function has no properties, this returned map will be empty. Note that some functions have multiple names. This function returns a map indexed by each alias it has for a given name. These names include both onnx and tensorflow names (which might be 1 or more)

Overrides:

mappingsForFunction in class DifferentialFunction

Returns:

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:

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:

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:

tensorflowNames

public String[] tensorflowNames()

Description copied from class: DifferentialFunction

The opName of this function tensorflow

Overrides:

tensorflowNames in class DifferentialFunction

Returns:

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