Package org.anchoranalysis.plugin.opencv.bean.object.segment.stack

Class SegmentObjectsFromTensorFlowModel

Object

AnchorBean<SegmentStackIntoObjectsPooled<OpenCVModel>>

InitializableBean<SegmentStackIntoObjectsPooled<OpenCVModel>,ImageInitialization>

ImageBean<SegmentStackIntoObjectsPooled<OpenCVModel>>

SegmentationBean<SegmentStackIntoObjectsPooled<OpenCVModel>>

SegmentStackIntoObjectsPooled<OpenCVModel>

SegmentStackIntoObjectsScaleDecode<org.opencv.core.Mat,OpenCVModel>

SegmentObjectsFromTensorFlowModel

public class SegmentObjectsFromTensorFlowModel
extends SegmentStackIntoObjectsScaleDecode<org.opencv.core.Mat,OpenCVModel>

Performs instance-segmentation using OpenCV's DNN module and a TensorFlow .pb SavedModel file.

Optionally a .pb.txt file may accompany it.

Author:

Owen Feehan

Constructor Summary

Constructors

Constructor	Description
SegmentObjectsFromTensorFlowModel()

Method Summary

Modifier and Type	Method	Description
ConcurrentModelPool<OpenCVModel>	createModelPool(ConcurrencyPlan plan, Logger logger)	Creates the model pool (to be used by multiple threads).
protected org.opencv.core.Mat	deriveInput(Stack stack, Optional<double[]> subtractMeans)	Derives the input tensor from an image.
String	getModelBinaryPath()	Relative-path to the TensorFlow model file, likely with .pb extension, relative to the models/ directory in the Anchor distribution.
String	getModelTextGraphPath()	Relative-path to the TensorFlow model file, likely with .pb.txt extension, relative to the models/ directory in the Anchor distribution.
protected Optional<String>	inputName()	The name of the tensor in the model which the input-image is mapped to.
void	setModelBinaryPath(String modelBinaryPath)	Relative-path to the TensorFlow model file, likely with .pb extension, relative to the models/ directory in the Anchor distribution.
void	setModelTextGraphPath(String modelTextGraphPath)	Relative-path to the TensorFlow model file, likely with .pb.txt extension, relative to the models/ directory in the Anchor distribution.

Methods inherited from class org.anchoranalysis.image.inference.bean.segment.instance.SegmentStackIntoObjectsScaleDecode

getClassLabelsPath, getDecode, getDisplayer, getInterpolator, getScaleInput, getSubtractMean, segment, setClassLabelsPath, setDecode, setDisplayer, setInterpolator, setScaleInput, setSubtractMean

Methods inherited from class org.anchoranalysis.image.inference.bean.segment.instance.SegmentStackIntoObjectsPooled

resolve, segment

Methods inherited from class org.anchoranalysis.bean.initializable.InitializableBean

getInitialization, getLogger, getPropertyInitializer, initialize, initializeRecursive, initRecursiveWithInitializer, isInitialized, onInitialization

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

SegmentObjectsFromTensorFlowModel

public SegmentObjectsFromTensorFlowModel()

Method Details

createModelPool

public ConcurrentModelPool<OpenCVModel> createModelPool(ConcurrencyPlan plan,
 Logger logger)
                                                 throws CreateModelFailedException

Description copied from class: SegmentStackIntoObjectsPooled

Creates the model pool (to be used by multiple threads).

Specified by:

createModelPool in class SegmentStackIntoObjectsPooled<OpenCVModel>

Parameters:

plan - the number and types of processors available for concurrent execution.

logger - the logger.

Returns:

the newly created model pool.

Throws:

CreateModelFailedException - if a model cannot be created.

deriveInput

protected org.opencv.core.Mat deriveInput(Stack stack,
 Optional<double[]> subtractMeans)
                                   throws OperationFailedException

Description copied from class: SegmentStackIntoObjectsScaleDecode

Derives the input tensor from an image.

Specified by:

deriveInput in class SegmentStackIntoObjectsScaleDecode<org.opencv.core.Mat,OpenCVModel>

Parameters:

stack - the image which is mapped into an input tensor.

subtractMeans - respective intensity values that are subtracted from the voxels before being added to the tensor (respectively for each channel).

Returns:

the tensor, representing the input image.

Throws:

OperationFailedException - if an input tensor cannot be created.

inputName

protected Optional<String> inputName()

Description copied from class: SegmentStackIntoObjectsScaleDecode

The name of the tensor in the model which the input-image is mapped to.

Specified by:

inputName in class SegmentStackIntoObjectsScaleDecode<org.opencv.core.Mat,OpenCVModel>

Returns:

the name.

getModelBinaryPath

public String getModelBinaryPath()

Relative-path to the TensorFlow model file, likely with .pb extension, relative to the models/ directory in the Anchor distribution.

setModelBinaryPath

public void setModelBinaryPath(String modelBinaryPath)

Relative-path to the TensorFlow model file, likely with .pb extension, relative to the models/ directory in the Anchor distribution.

getModelTextGraphPath

public String getModelTextGraphPath()

Relative-path to the TensorFlow model file, likely with .pb.txt extension, relative to the models/ directory in the Anchor distribution.

If empty, then no such file is specified.

setModelTextGraphPath

public void setModelTextGraphPath(String modelTextGraphPath)

Relative-path to the TensorFlow model file, likely with .pb.txt extension, relative to the models/ directory in the Anchor distribution.

If empty, then no such file is specified.