CustomObjectDetectorOptions.Builder

AI-generated Key Takeaways

• CustomObjectDetectorOptions.Builder helps create customized object detection options using local or remote models.

• It allows enabling object classification and multiple object detection within an image.

• Developers can configure detection mode, classification confidence threshold, and maximum labels per object.

• A custom Executor can be set for task execution, otherwise, an internal background thread pool is used.

• Calling build() on the builder creates a CustomObjectDetectorOptions instance with the specified settings.

public static class CustomObjectDetectorOptions.Builder extends Object

Builder of CustomObjectDetectorOptions.

Public Constructor Summary

	Builder(LocalModel localModel) Creates a new builder to build CustomObjectDetectorOptions with LocalModel.
	Builder(CustomRemoteModel remoteModel) Creates a new builder to build CustomObjectDetectorOptions with CustomRemoteModel.

Public Method Summary

CustomObjectDetectorOptions	build()
CustomObjectDetectorOptions.Builder	enableClassification() Enables classification.
CustomObjectDetectorOptions.Builder	enableMultipleObjects() Enables multiple objects for detection.
CustomObjectDetectorOptions.Builder	setClassificationConfidenceThreshold(float classificationConfidenceThreshold) Sets the classification confidence threshold of labels to be detected.
CustomObjectDetectorOptions.Builder	setDetectorMode(int detectorMode) Sets the DetectorMode, which contains two modes, ObjectDetectorOptionsBase.STREAM_MODE and ObjectDetectorOptionsBase.SINGLE_IMAGE_MODE.
CustomObjectDetectorOptions.Builder	setExecutor(Executor executor) Sets the custom Executor to use.
CustomObjectDetectorOptions.Builder	setMaxPerObjectLabelCount(int maxPerObjectLabelCount) Sets the maximum number of labels per object that the detector will return.

Inherited Method Summary

From class java.lang.Object

Object	clone()
boolean	equals(Object arg0)
void	finalize()
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

Public Constructors

public Builder (LocalModel localModel)

Creates a new builder to build CustomObjectDetectorOptions with LocalModel.

public Builder (CustomRemoteModel remoteModel)

Creates a new builder to build CustomObjectDetectorOptions with CustomRemoteModel.

Public Methods

public CustomObjectDetectorOptions build ()

public CustomObjectDetectorOptions.Builder enableClassification ()

Enables classification.

By default, the classification is off.

public CustomObjectDetectorOptions.Builder enableMultipleObjects ()

Enables multiple objects for detection.

When enabled, the maximum number of detected objects per image is 5.

By default, the detector detects prominent object only.

public CustomObjectDetectorOptions.Builder setClassificationConfidenceThreshold (float classificationConfidenceThreshold)

Sets the classification confidence threshold of labels to be detected.

If not set, any classifier threshold specified by the model’s metadata will be used, or 0.0 will be used if no such metadata or threshold.

public CustomObjectDetectorOptions.Builder setDetectorMode (int detectorMode)

Sets the DetectorMode, which contains two modes, ObjectDetectorOptionsBase.STREAM_MODE and ObjectDetectorOptionsBase.SINGLE_IMAGE_MODE. For more details, please see comments for ObjectDetectorOptionsBase.STREAM_MODE and ObjectDetectorOptionsBase.SINGLE_IMAGE_MODE.

By default, it is ObjectDetectorOptionsBase.STREAM_MODE.

public CustomObjectDetectorOptions.Builder setExecutor (Executor executor)

Sets the custom Executor to use. If no Executor is set, an internal background thread pool will be used.

Most clients should not need to call this method.

Parameters

executor	the Executor to use

Returns

• this object, for chaining method calls

public CustomObjectDetectorOptions.Builder setMaxPerObjectLabelCount (int maxPerObjectLabelCount)

Sets the maximum number of labels per object that the detector will return.

If not set, the default value of 10 will be used.