T
- tensor-type, depending on which framework is used.public abstract class DecodeInstanceSegmentation<T> extends AnchorBean<DecodeInstanceSegmentation<T>>
Constructor and Description |
---|
DecodeInstanceSegmentation() |
Modifier and Type | Method and Description |
---|---|
abstract List<LabelledWithConfidence<MultiScaleObject>> |
decode(List<T> inferenceOutput,
ImageInferenceContext context)
Decodes the output tensors from inference into
ObjectMask s with confidence and
labels. |
abstract List<String> |
expectedOutputs()
Ordered names of the tensors we are interested in processing, as outputted from inference.
|
checkMisconfigured, describeBean, describeChildren, duplicateBean, fields, findFieldsOfClass, getBeanName, getLocalPath, localise, toString
public abstract List<LabelledWithConfidence<MultiScaleObject>> decode(List<T> inferenceOutput, ImageInferenceContext context) throws OperationFailedException
ObjectMask
s with confidence and
labels.
The created ObjectMask
s should match unscaledDimensions
in size.
inferenceOutput
- the tensors that are the result of the inference.context
- the context in which the inference is occurring.unscaledDimensions
in size.OperationFailedException
- if it cannot be decoded successfully.Copyright © 2010–2023 Owen Feehan, ETH Zurich, University of Zurich, Hoffmann-La Roche. All rights reserved.