Package org.anchoranalysis.image.inference.bean.segment.instance

Class DecodeInstanceSegmentation<T>

Object

AnchorBean<DecodeInstanceSegmentation<T>>

DecodeInstanceSegmentation<T>

Type Parameters:

T - tensor-type, depending on which framework is used.

Direct Known Subclasses:

DecodeEAST, DecodeMaskRCNN

public abstract class DecodeInstanceSegmentation<T>
extends AnchorBean<DecodeInstanceSegmentation<T>>

Decodes inference output into segmented-objects.

Author:

Owen Feehan

Constructor Summary

Constructors

Constructor	Description
DecodeInstanceSegmentation()

Method Summary

Modifier and Type	Method	Description
abstract List<LabelledWithConfidence<MultiScaleObject>>	decode(List<T> inferenceOutput, ImageInferenceContext context)	Decodes the output tensors from inference into ObjectMasks with confidence and labels.
abstract List<String>	expectedOutputs()	Ordered names of the tensors we are interested in processing, as outputted from inference.

Methods inherited from class org.anchoranalysis.bean.AnchorBean

checkMisconfigured, describeBean, describeChildren, duplicateBean, fields, findFieldsOfClass, getBeanName, getLocalPath, localise, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Details

DecodeInstanceSegmentation

public DecodeInstanceSegmentation()

Method Details

decode

public abstract List<LabelledWithConfidence<MultiScaleObject>> decode(List<T> inferenceOutput,
 ImageInferenceContext context)
                                                               throws OperationFailedException

Decodes the output tensors from inference into ObjectMasks with confidence and labels.

The created ObjectMasks should match unscaledDimensions in size.

Parameters:

inferenceOutput - the tensors that are the result of the inference.

context - the context in which the inference is occurring.

Returns:

a newly created list of objects, with associated confidence, and labels, that matches unscaledDimensions in size.

Throws:

OperationFailedException - if it cannot be decoded successfully.

expectedOutputs

public abstract List<String> expectedOutputs()

Ordered names of the tensors we are interested in processing, as outputted from inference.

Returns:

the list of names, as above.