Class CropAndResize
- java.lang.Object
-
- org.nd4j.autodiff.functions.DifferentialFunction
-
- org.nd4j.linalg.api.ops.DynamicCustomOp
-
- org.nd4j.linalg.api.ops.impl.image.CropAndResize
-
- All Implemented Interfaces:
CustomOp
public class CropAndResize extends DynamicCustomOp
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description static classCropAndResize.Method-
Nested classes/interfaces inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp
DynamicCustomOp.DynamicCustomOpsBuilder
-
-
Field Summary
Fields Modifier and Type Field Description protected doubleextrapolationValueprotected CropAndResize.Methodmethod-
Fields inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp
axis, bArguments, dArguments, iArguments, inplaceCall, inputArguments, outputArguments, outputVariables, sArguments, tArguments
-
Fields inherited from class org.nd4j.autodiff.functions.DifferentialFunction
dimensions, extraArgs, inPlace, ownName, ownNameSetWithDefault, sameDiff, scalarValue
-
-
Constructor Summary
Constructors Constructor Description CropAndResize(@NonNull SameDiff sameDiff, @NonNull SDVariable image, @NonNull SDVariable cropBoxes, @NonNull SDVariable boxIndices, @NonNull SDVariable cropOutSize, @NonNull CropAndResize.Method method, double extrapolationValue)CropAndResize(@NonNull SameDiff sameDiff, SDVariable image, SDVariable cropBoxes, SDVariable boxIndices, SDVariable cropOutSize, double extrapolationValue)CropAndResize(@NonNull INDArray image, @NonNull INDArray cropBoxes, @NonNull INDArray boxIndices, @NonNull INDArray cropOutSize, @NonNull CropAndResize.Method method, double extrapolationValue, INDArray output)CropAndResize(INDArray image, INDArray cropBoxes, INDArray boxIndices, INDArray cropOutSize, double extrapolationValue)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description protected voidaddArgs()List<DataType>calculateOutputDataTypes(List<DataType> inputDataTypes)Calculate the data types for the output arrays.List<SDVariable>doDiff(List<SDVariable> f1)The actual implementation for automatic differentiation.voidinitFromTensorFlow(NodeDef nodeDef, SameDiff initWith, Map<String,AttrValue> attributesForNode, GraphDef graph)Initialize the function from the givenNodeDefStringopName()This method returns op opName as stringStringtensorflowName()The opName of this function tensorflow-
Methods inherited from class org.nd4j.linalg.api.ops.DynamicCustomOp
addBArgument, addDArgument, addIArgument, addIArgument, addInputArgument, addOutputArgument, addOutputsToOp, addSArgument, addTArgument, assertValidForExecution, bArgs, builder, calculateOutputShape, calculateOutputShape, clearArrays, computeArrays, configureFromArguments, dArgs, generateFake, generateFake, getBArgument, getDescriptor, getIArgument, getInputArgument, getOutputArgument, getSArgument, getTArgument, getValue, iArgs, initFromOnnx, inputArguments, mappingsForFunction, numBArguments, numDArguments, numIArguments, numInputArguments, numOutputArguments, numSArguments, numTArguments, onnxName, opHash, opNum, opType, outputArguments, outputVariables, outputVariables, propertiesForFunction, removeIArgument, removeInputArgument, removeOutputArgument, removeSArgument, removeTArgument, sArgs, setInputArgument, setInputArguments, setOutputArgument, setPropertiesForFunction, setValueFor, tArgs, toString, wrapFilterNull, wrapOrNull, wrapOrNull
-
Methods inherited from class org.nd4j.autodiff.functions.DifferentialFunction
arg, arg, argNames, args, attributeAdaptersForFunction, configFieldName, configureWithSameDiff, diff, dup, equals, getBooleanFromProperty, getDoubleValueFromProperty, getIntValueFromProperty, getLongValueFromProperty, getNumOutputs, getStringFromProperty, hashCode, isConfigProperties, larg, onnxNames, outputs, outputVariable, outputVariablesNames, rarg, replaceArg, setInstanceId, 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
isInplaceCall
-
-
-
-
Field Detail
-
method
protected CropAndResize.Method method
-
extrapolationValue
protected double extrapolationValue
-
-
Constructor Detail
-
CropAndResize
public CropAndResize(@NonNull @NonNull SameDiff sameDiff, @NonNull @NonNull SDVariable image, @NonNull @NonNull SDVariable cropBoxes, @NonNull @NonNull SDVariable boxIndices, @NonNull @NonNull SDVariable cropOutSize, @NonNull @NonNull CropAndResize.Method method, double extrapolationValue)
-
CropAndResize
public CropAndResize(@NonNull @NonNull SameDiff sameDiff, SDVariable image, SDVariable cropBoxes, SDVariable boxIndices, SDVariable cropOutSize, double extrapolationValue)
-
CropAndResize
public CropAndResize(@NonNull @NonNull INDArray image, @NonNull @NonNull INDArray cropBoxes, @NonNull @NonNull INDArray boxIndices, @NonNull @NonNull INDArray cropOutSize, @NonNull @NonNull CropAndResize.Method method, double extrapolationValue, INDArray output)
-
-
Method Detail
-
opName
public String opName()
Description copied from class:DynamicCustomOpThis method returns op opName as string- Specified by:
opNamein interfaceCustomOp- Overrides:
opNamein classDynamicCustomOp- Returns:
-
tensorflowName
public String tensorflowName()
Description copied from class:DifferentialFunctionThe opName of this function tensorflow- Overrides:
tensorflowNamein classDynamicCustomOp- Returns:
-
initFromTensorFlow
public void initFromTensorFlow(NodeDef nodeDef, SameDiff initWith, Map<String,AttrValue> attributesForNode, GraphDef graph)
Description copied from class:DifferentialFunctionInitialize the function from the givenNodeDef- Overrides:
initFromTensorFlowin classDynamicCustomOp
-
addArgs
protected void addArgs()
-
doDiff
public List<SDVariable> doDiff(List<SDVariable> f1)
Description copied from class:DifferentialFunctionThe actual implementation for automatic differentiation.- Overrides:
doDiffin classDynamicCustomOp- Returns:
-
calculateOutputDataTypes
public List<DataType> calculateOutputDataTypes(List<DataType> inputDataTypes)
Description copied from class:DifferentialFunctionCalculate the data types for the output arrays. Though datatypes can also be inferred fromDifferentialFunction.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:
calculateOutputDataTypesin classDifferentialFunction- Parameters:
inputDataTypes- The data types of the inputs- Returns:
- The data types of the outputs
-
-