If a delegate implementation holds additional resources or memory that should be explicitly
freed, then best practice is to add a close() method to the implementation and have the
client call that explicitly when the delegate instance is no longer in use. While this approach
technically allows sharing of a single delegate instance across multiple interpreter instances,
the delegate implementation must explicitly support this.
Returns a native handle to the TensorFlow Lite delegate implementation.
Inherited Methods
From interface
java.io.Closeable
abstract
void
close()
From interface
java.lang.AutoCloseable
abstract
void
close()
Public Methods
public
void
close()
Closes the delegate and releases any resources associated with it.
In contrast to the method declared in the base Closeable interface, this method
does not throw checked exceptions.
public
abstract
long
getNativeHandle()
Returns a native handle to the TensorFlow Lite delegate implementation.
Note: The Java Delegate maintains ownership of the native delegate instance, and
must ensure its existence for the duration of usage with any InterpreterApi instance.
Note: the native delegate instance may not be created until the delegate has been attached
to an interpreter, so this method should not be called until after an interpreter has been
constructed with this delegate.
Returns
The native delegate handle. In C/C++, this should be a pointer to
'TfLiteOpaqueDelegate'.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-05-10 UTC."],[],[],null,["# Delegate\n\npublic interface **Delegate** \n\n|---|---|---|\n| Known Indirect Subclasses [GpuDelegate](/edge/api/tflite/java/org/tensorflow/lite/gpu/GpuDelegate) |--------------------------------------------------------------------------|-----------------------------------------------------------------------------------| | [GpuDelegate](/edge/api/tflite/java/org/tensorflow/lite/gpu/GpuDelegate) | [Delegate](/edge/api/tflite/java/org/tensorflow/lite/Delegate) for GPU inference. | |||\n\nWrapper for a native TensorFlow Lite Delegate.\n\nIf a delegate implementation holds additional resources or memory that should be explicitly\nfreed, then best practice is to add a `close()` method to the implementation and have the\nclient call that explicitly when the delegate instance is no longer in use. While this approach\ntechnically allows sharing of a single delegate instance across multiple interpreter instances,\nthe delegate implementation must explicitly support this.\n\n\u003cbr /\u003e\n\n### Public Methods\n\n|---------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| void | [close](/edge/api/tflite/java/org/tensorflow/lite/Delegate#close())() Closes the delegate and releases any resources associated with it. |\n| abstract long | [getNativeHandle](/edge/api/tflite/java/org/tensorflow/lite/Delegate#getNativeHandle())() Returns a native handle to the TensorFlow Lite delegate implementation. |\n\n### Inherited Methods\n\nFrom interface java.io.Closeable \n\n|---------------|---------|\n| abstract void | close() |\n\nFrom interface java.lang.AutoCloseable \n\n|---------------|---------|\n| abstract void | close() |\n\nPublic Methods\n--------------\n\n#### public void\n**close**\n()\n\nCloses the delegate and releases any resources associated with it.\n\nIn contrast to the method declared in the base [Closeable](https://developer.android.com/reference/java/io/Closeable.html) interface, this method\ndoes not throw checked exceptions.\n\n\u003cbr /\u003e\n\n#### public abstract long\n**getNativeHandle**\n()\n\nReturns a native handle to the TensorFlow Lite delegate implementation.\n\nNote: The Java [Delegate](/edge/api/tflite/java/org/tensorflow/lite/Delegate) maintains ownership of the native delegate instance, and\nmust ensure its existence for the duration of usage with any [InterpreterApi](/edge/api/tflite/java/org/tensorflow/lite/InterpreterApi) instance.\n\nNote: the native delegate instance may not be created until the delegate has been attached\nto an interpreter, so this method should not be called until after an interpreter has been\nconstructed with this delegate.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n##### Returns\n\n- The native delegate handle. In C/C++, this should be a pointer to 'TfLiteOpaqueDelegate'. \n\n##### Throws\n\n| [IllegalStateException](https://developer.android.com/reference/java/lang/IllegalStateException.html) | if called before the native delegate instance has been constructed. |\n|-------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------|"]]
