public class FakeQuantWithMinMaxVarsPerChannel extends DynamicCustomOp
DynamicCustomOp.DynamicCustomOpsBuilder
Modifier and Type | Field and Description |
---|---|
protected boolean |
narrowRange |
protected int |
numBits |
axis, bArguments, dArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, tArguments
dimensions, extraArgs, inPlace, ownName, ownNameSetWithDefault, sameDiff, scalarValue
Constructor and Description |
---|
FakeQuantWithMinMaxVarsPerChannel() |
FakeQuantWithMinMaxVarsPerChannel(INDArray x,
INDArray min,
INDArray max) |
FakeQuantWithMinMaxVarsPerChannel(INDArray x,
INDArray min,
INDArray max,
boolean narrow) |
FakeQuantWithMinMaxVarsPerChannel(INDArray x,
INDArray min,
INDArray max,
int num_bits) |
FakeQuantWithMinMaxVarsPerChannel(INDArray x,
INDArray min,
INDArray max,
int num_bits,
boolean narrow) |
FakeQuantWithMinMaxVarsPerChannel(SameDiff sameDiff,
SDVariable x,
SDVariable min,
SDVariable max,
int num_bits,
boolean narrow) |
Modifier and Type | Method and Description |
---|---|
List<DataType> |
calculateOutputDataTypes(List<DataType> inputDataTypes)
Calculate the data types for the output arrays.
|
void |
initFromTensorFlow(NodeDef nodeDef,
SameDiff initWith,
Map<String,AttrValue> attributesForNode,
GraphDef graph)
Initialize the function from the given
NodeDef |
String |
opName()
This method returns op opName as string
|
String |
tensorflowName()
The opName of this function tensorflow
|
addBArgument, addDArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addTArgument, assertValidForExecution, bArgs, builder, calculateOutputShape, calculateOutputShape, clearArrays, dArgs, doDiff, getBArgument, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getTArgument, iArgs, initFromOnnx, inputArguments, numBArguments, numDArguments, numIArguments, numInputArguments, numOutputArguments, numTArguments, onnxName, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, removeIArgument, removeInputArgument, removeOutputArgument, removeTArgument, setInputArgument, setInputArguments, setOutputArgument, tArgs, 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
public FakeQuantWithMinMaxVarsPerChannel()
public FakeQuantWithMinMaxVarsPerChannel(INDArray x, INDArray min, INDArray max, int num_bits, boolean narrow)
public FakeQuantWithMinMaxVarsPerChannel(INDArray x, INDArray min, INDArray max, int num_bits)
public FakeQuantWithMinMaxVarsPerChannel(INDArray x, INDArray min, INDArray max, boolean narrow)
public FakeQuantWithMinMaxVarsPerChannel(INDArray x, INDArray min, INDArray max)
public FakeQuantWithMinMaxVarsPerChannel(SameDiff sameDiff, SDVariable x, SDVariable min, SDVariable max, int num_bits, boolean narrow)
public String opName()
DynamicCustomOp
opName
in interface CustomOp
opName
in class DynamicCustomOp
public String tensorflowName()
DifferentialFunction
tensorflowName
in class DynamicCustomOp
public void initFromTensorFlow(NodeDef nodeDef, SameDiff initWith, Map<String,AttrValue> attributesForNode, GraphDef graph)
DifferentialFunction
NodeDef
initFromTensorFlow
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 © 2021. All rights reserved.