tensorflutt

Description:

tensorflutt

Overview #
TensorFlow Lite Flutter plugin provides a flexible and fast solution for accessing TensorFlow Lite interpreter and performing inference. The API is similar to the TFLite Java and Swift APIs. It directly binds to TFLite C API making it efficient (low-latency). Offers acceleration support using NNAPI, GPU delegates on Android, Metal and CoreML delegates on iOS, and XNNPack delegate on Desktop platforms.
Key Features #

Multi-platform Support for Android, iOS, Windows, Mac, Linux.
Flexibility to use any TFLite Model.
Acceleration using multi-threading and delegate support.
Similar structure as TensorFlow Lite Java API.
Inference speeds close to native Android Apps built using the Java API.
You can choose to use any TensorFlow version by building binaries locally.
Run inference in different isolates to prevent jank in UI thread.

(Important) Initial setup : Add dynamic libraries to your app #
Android #


Place the script install.sh (Linux/Mac) or install.bat (Windows) at the root of your project.


Execute sh install.sh (Linux) / install.bat (Windows) at the root of your project to automatically download and place binaries at appropriate folders.
Note: The binaries installed will not include support for GpuDelegateV2 and NnApiDelegate however InterpreterOptions().useNnApiForAndroid can still be used.


Use sh install.sh -d (Linux) or install.bat -d (Windows) instead if you wish to use these GpuDelegateV2 and NnApiDelegate.


These scripts install pre-built binaries based on latest stable tensorflow release. For info about using other tensorflow versions follow instructions in wiki.
iOS #

Download TensorFlowLiteC.framework. For building a custom version of tensorflow, follow instructions in wiki.
Place the TensorFlowLiteC.framework in the pub-cache folder of this package.

Pub-Cache folder location: (ref)

~/.pub-cache/hosted/pub.dartlang.org/tflite_flutter-<plugin-version>/ios/ (Linux/ Mac)
%LOCALAPPDATA%\Pub\Cache\hosted\pub.dartlang.org\tflite_flutter-<plugin-version>\ios\ (Windows)

Desktop #
Follow instructions in this guide to build and use desktop binaries.
TFLite Flutter Helper Library #
A dedicated library with simple architecture for processing and manipulating input and output of TFLite Models. API design and documentation is identical to the TensorFlow Lite Android Support Library. Strongly recommended to be used with tflite_flutter_plugin. Learn more.
Examples #



Title
Code
Demo
Blog




Text Classification App
Code

Blog/Tutorial


Image Classification App
Code

-


Object Detection App
Code

Blog/Tutorial


Reinforcement Learning App
Code

Blog/Tutorial



Import #
import 'package:tflite_flutter/tflite_flutter.dart';
copied to clipboard
Usage instructions #
Creating the Interpreter #


From asset
Place your_model.tflite in assets directory. Make sure to include assets in pubspec.yaml.
final interpreter = await tfl.Interpreter.fromAsset('your_model.tflite');
copied to clipboard


Refer to the documentation for info on creating interpreter from buffer or file.
Performing inference #
See TFLite Flutter Helper Library for easy processing of input and output.


For single input and output
Use void run(Object input, Object output).
// For ex: if input tensor shape [1,5] and type is float32
var input = [[1.23, 6.54, 7.81. 3.21, 2.22]];

// if output tensor shape [1,2] and type is float32
var output = List.filled(1*2, 0).reshape([1,2]);

// inference
interpreter.run(input, output);

// print the output
print(output);
copied to clipboard


For multiple inputs and outputs
Use void runForMultipleInputs(List<Object> inputs, Map<int, Object> outputs).
var input0 = [1.23];
var input1 = [2.43];

// input: List<Object>
var inputs = [input0, input1, input0, input1];

var output0 = List<double>.filled(1, 0);
var output1 = List<double>.filled(1, 0);

// output: Map<int, Object>
var outputs = {0: output0, 1: output1};

// inference
interpreter.runForMultipleInputs(inputs, outputs);

// print outputs
print(outputs)
copied to clipboard


Closing the interpreter #
interpreter.close();
copied to clipboard
Improve performance using delegate support #
Note: This feature is under testing and could be unstable with some builds and on some devices.
copied to clipboard


NNAPI delegate for Android
var interpreterOptions = InterpreterOptions()..useNnApiForAndroid = true;
final interpreter = await Interpreter.fromAsset('your_model.tflite',
options: interpreterOptions);

copied to clipboard
or
var interpreterOptions = InterpreterOptions()..addDelegate(NnApiDelegate());
final interpreter = await Interpreter.fromAsset('your_model.tflite',
options: interpreterOptions);

copied to clipboard


GPU delegate for Android and iOS


Android GpuDelegateV2
final gpuDelegateV2 = GpuDelegateV2(
options: GpuDelegateOptionsV2(
false,
TfLiteGpuInferenceUsage.fastSingleAnswer,
TfLiteGpuInferencePriority.minLatency,
TfLiteGpuInferencePriority.auto,
TfLiteGpuInferencePriority.auto,
));

var interpreterOptions = InterpreterOptions()..addDelegate(gpuDelegateV2);
final interpreter = await Interpreter.fromAsset('your_model.tflite',
options: interpreterOptions);
copied to clipboard


iOS Metal Delegate (GpuDelegate)
final gpuDelegate = GpuDelegate(
options: GpuDelegateOptions(true, TFLGpuDelegateWaitType.active),
);
var interpreterOptions = InterpreterOptions()..addDelegate(gpuDelegate);
final interpreter = await Interpreter.fromAsset('your_model.tflite',
options: interpreterOptions);
copied to clipboard




Refer Tests to see more example code for each method.
Credits #

Tian LIN, Jared Duke, Andrew Selle, YoungSeok Yoon, Shuangfeng Li from the TensorFlow Lite Team for their invaluable guidance.
Authors of dart-lang/tflite_native.