tflite 0.0.2

  • README.md
  • CHANGELOG.md
  • Example
  • Installing
  • Versions
  • new73

tflite

A Flutter plugin for accessing TensorFlow Lite. Supports both iOS and Android.

Installation

Add tflite as a dependency in your pubspec.yaml file.

Android

In android/app/build.gradle file add the following setting in android block.

    aaptOptions {
        noCompress 'tflite'
    }

Usage

  1. Create a assets folder and place your label file and model file in it. In pubspec.yaml add:
  assets:
   - assets/labels.txt
   - assets/mobilenet_v1_1.0_224.tflite
  1. Import the library:
import 'package:tflite/tflite.dart';
  1. Load the model and labels:
String res = await Tflite.loadModel(
  model: "assets/mobilenet_v1_1.0_224.tflite",
  labels: "assets/labels.txt",
);
  1. Run the model on a image file:
var recognitions = await Tflite.runModelOnImage(
  path: filepath,   // required
  inputSize: 224,   // wanted input size, defaults to 224
  numChannels: 3,   // wanted input channels, defaults to 3
  imageMean: 127.5, // defaults to 117.0
  imageStd: 127.5,  // defaults to 1.0
  numResults: 6,    // defaults to 5
  threshold: 0.05,  // defaults to 0.1
  numThreads: 1,    // defaults to 1
);
  1. Release resources
await Tflite.close();

Demo

Refer to the example.

0.0.2

  • Fixed link.

0.0.1

  • Initial release.

example/lib/main.dart

import 'dart:async';
import 'dart:io';
import 'package:flutter/material.dart';
import 'package:flutter/services.dart';

import 'package:tflite/tflite.dart';
import 'package:image_picker/image_picker.dart';

void main() => runApp(new MyApp());

class MyApp extends StatefulWidget {
  @override
  _MyAppState createState() => new _MyAppState();
}

class _MyAppState extends State<MyApp> {
  File _image;
  List _recognitions;

  Future getImage() async {
    var image = await ImagePicker.pickImage(source: ImageSource.camera);
    recognizeImage(image);
    setState(() {
      _image = image;
    });
  }

  @override
  void initState() {
    super.initState();
    loadModel();
  }

  Future loadModel() async {
    try {
      String res = await Tflite.loadModel(
        model: "assets/mobilenet_v1_1.0_224.tflite",
        labels: "assets/labels.txt",
      );
      print(res);
    } on PlatformException {
      print('Failed to load model.');
    }
  }

  Future recognizeImage(File image) async {
    var recognitions = await Tflite.runModelOnImage(
      path: image.path,
      numResults: 6,
      threshold: 0.05,
    );
    print(recognitions);
    setState(() {
      _recognitions = recognitions;
    });
    // await Tflite.close();
  }

  @override
  Widget build(BuildContext context) {
    return MaterialApp(
      home: Scaffold(
        appBar: AppBar(
          title: const Text('tflite example app'),
        ),
        body: Stack(
          children: <Widget>[
            Center(
              child: _image == null
                  ? Text('No image selected.')
                  : Image.file(_image),
            ),
            Center(
              child: Column(
                children: _recognitions != null
                    ? _recognitions.map((res) {
                        return Text(
                          "${res["index"]} - ${res["label"]}: ${res["confidence"].toString()}",
                          style: TextStyle(
                            color: Colors.black,
                            fontSize: 20.0,
                            background: Paint()..color = Colors.white,
                          ),
                        );
                      }).toList()
                    : [],
              ),
            ),
          ],
        ),
        floatingActionButton: FloatingActionButton(
          onPressed: getImage,
          tooltip: 'Pick Image',
          child: Icon(Icons.add_a_photo),
        ),
      ),
    );
  }
}

Use this package as a library

1. Depend on it

Add this to your package's pubspec.yaml file:


dependencies:
  tflite: ^0.0.2

2. Install it

You can install packages from the command line:

with Flutter:


$ flutter packages get

Alternatively, your editor might support flutter packages get. Check the docs for your editor to learn more.

3. Import it

Now in your Dart code, you can use:


import 'package:tflite/tflite.dart';
  
Version Uploaded Documentation Archive
0.0.2 Sep 23, 2018 Go to the documentation of tflite 0.0.2 Download tflite 0.0.2 archive
0.0.1 Sep 23, 2018 Go to the documentation of tflite 0.0.1 Download tflite 0.0.1 archive
Popularity:
Describes how popular the package is relative to other packages. [more]
58
Health:
Code health derived from static analysis. [more]
100
Maintenance:
Reflects how tidy and up-to-date the package is. [more]
70
Overall:
Weighted score of the above. [more]
73
Learn more about scoring.

We analyzed this package on Oct 10, 2018, and provided a score, details, and suggestions below. Analysis was completed with status completed using:

  • Dart: 2.0.0
  • pana: 0.12.4
  • Flutter: 0.9.5

Platforms

Detected platforms: Flutter

References Flutter, and has no conflicting libraries.

Maintenance suggestions

The description is too short. (-20 points)

Add more detail about the package, what it does and what is its target use case. Try to write at least 60 characters.

Package is pre-v0.1 release. (-10 points)

While there is nothing inherently wrong with versions of 0.0.*, it usually means that the author is still experimenting with the general direction of the API.

Dependencies

Package Constraint Resolved Available
Direct dependencies
Dart SDK >=2.0.0-dev.68.0 <3.0.0
flutter 0.0.0
Transitive dependencies
collection 1.14.11
meta 1.1.6
sky_engine 0.0.99
typed_data 1.1.6
vector_math 2.0.8