org.tensorflow.lite

Class Interpreter.Options

java.lang.Object

org.tensorflow.lite.Interpreter.Options

Enclosing class:

Interpreter

public static class Interpreter.Options
extends Object

An options class for controlling runtime interpreter behavior.

Constructor Summary

Constructors

Constructor and Description
Options()

Method Summary

Modifier and Type	Method and Description
Interpreter.Options	setAllowFp16PrecisionForFp32(boolean allow) Sets whether to allow float16 precision for FP32 calculation when possible.
Interpreter.Options	setNumThreads(int numThreads) Sets the number of threads to be used for ops that support multi-threading.
Interpreter.Options	setUseNNAPI(boolean useNNAPI) Sets whether to use NN API (if available) for op execution.

Methods inherited from class java.lang.Object

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

Constructor Detail

Options

public Options()

Method Detail

setNumThreads

public Interpreter.Options setNumThreads(int numThreads)

Sets the number of threads to be used for ops that support multi-threading. Defaults to a platform-dependent value.

setUseNNAPI

public Interpreter.Options setUseNNAPI(boolean useNNAPI)

Sets whether to use NN API (if available) for op execution. Defaults to false (disabled).

setAllowFp16PrecisionForFp32

public Interpreter.Options setAllowFp16PrecisionForFp32(boolean allow)

Sets whether to allow float16 precision for FP32 calculation when possible. Defaults to false (disallow). WARNING: This is an experimental API and subject to change.