public class Pooling2D extends DynamicCustomOp
Modifier and Type | Class and Description |
---|---|
static class |
Pooling2D.Divisor
Divisor mode for average pooling only.
|
static class |
Pooling2D.Pooling2DType |
DynamicCustomOp.DynamicCustomOpsBuilder
Modifier and Type | Field and Description |
---|---|
protected Pooling2DConfig |
config |
axis, bArguments, dArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, tArguments
dimensions, extraArgs, inPlace, sameDiff, scalarValue
Constructor and Description |
---|
Pooling2D() |
Pooling2D(@NonNull INDArray[] inputs,
INDArray[] outputs,
@NonNull Pooling2DConfig config) |
Pooling2D(@NonNull INDArray input,
INDArray output,
@NonNull Pooling2DConfig config) |
Pooling2D(SameDiff sameDiff,
SDVariable[] inputs,
Pooling2DConfig config) |
Modifier and Type | Method and Description |
---|---|
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.
|
String |
getPoolingPrefix() |
long[] |
iArgs() |
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.
|
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
|
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, tensorflowName, toString, wrapFilterNull, wrapOrNull, wrapOrNull
arg, arg, argNames, args, attributeAdaptersForFunction, diff, dup, equals, getNumOutputs, getValue, hashCode, larg, mappingsForFunction, onnxNames, outputs, outputVariable, outputVariablesNames, rarg, replaceArg, setInstanceId, setPropertiesForFunction, setValueFor, tensorflowNames
clone, finalize, getClass, notify, notifyAll, wait, wait, wait
isInplaceCall
protected Pooling2DConfig config
public Pooling2D()
public Pooling2D(SameDiff sameDiff, SDVariable[] inputs, Pooling2DConfig config)
public Pooling2D(@NonNull @NonNull INDArray[] inputs, INDArray[] outputs, @NonNull @NonNull Pooling2DConfig config)
public Pooling2D(@NonNull @NonNull INDArray input, INDArray output, @NonNull @NonNull Pooling2DConfig config)
public long[] iArgs()
iArgs
in interface CustomOp
iArgs
in class DynamicCustomOp
public Map<String,Object> propertiesForFunction()
DifferentialFunction
propertiesForFunction
in class DifferentialFunction
public boolean isConfigProperties()
DifferentialFunction
isConfigProperties
in class DifferentialFunction
public String configFieldName()
DifferentialFunction
DifferentialFunction.isConfigProperties()
to facilitate mapping fields for model import.configFieldName
in class DifferentialFunction
public String opName()
DynamicCustomOp
opName
in interface CustomOp
opName
in class DynamicCustomOp
public List<SDVariable> doDiff(List<SDVariable> f1)
DifferentialFunction
doDiff
in class DynamicCustomOp
public void initFromTensorFlow(NodeDef nodeDef, SameDiff initWith, Map<String,AttrValue> attributesForNode, GraphDef graph)
DifferentialFunction
NodeDef
initFromTensorFlow
in class DynamicCustomOp
public void initFromOnnx(Onnx.NodeProto node, SameDiff initWith, Map<String,Onnx.AttributeProto> attributesForNode, Onnx.GraphProto graph)
DifferentialFunction
Onnx.NodeProto
initFromOnnx
in class DynamicCustomOp
public String getPoolingPrefix()
public String onnxName()
DifferentialFunction
onnxName
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.