tflite

A Flutter plugin for accessing TensorFlow Lite API. Supports Classification and Object Detection on both iOS and Android.

Breaking changes since 1.0.0:

Updated to TensorFlow Lite API v1.12.0.
No longer accepts parameter inputSize and numChannels. They will be retrieved from input tensor.
numThreads is moved to Tflite.loadModel.

Installation

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

Android

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

    aaptOptions {
        noCompress 'tflite'
    }

iOS

If you get error like "'vector' file not found", please open ios/Runner.xcworkspace in Xcode, click Runner > Tagets > Runner > Build Settings, search Compile Sources As, change the value to Objective-C++;

Usage

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

Import the library:

import 'package:tflite/tflite.dart';

Load the model and labels:

String res = await Tflite.loadModel(
  model: "assets/mobilenet_v1_1.0_224.tflite",
  labels: "assets/labels.txt",
  numThreads: 1 // defaults to 1
);

See Image Classication and Object Detection below.
Release resources:

await Tflite.close();

Image Classification

Output fomart:

{
  index: 0,
  label: "person",
  confidence: 0.629
}

Run on image:

var recognitions = await Tflite.runModelOnImage(
  path: filepath,   // required
  imageMean: 0.0,   // defaults to 117.0
  imageStd: 255.0,  // defaults to 1.0
  numResults: 2,    // defaults to 5
  threshold: 0.2    // defaults to 0.1
);

Run on binary:

var recognitions = await Tflite.runModelOnBinary(
  binary: imageToByteListFloat32(image, 224, 127.5, 127.5),// required
  numResults: 6,    // defaults to 5
  threshold: 0.05,  // defaults to 0.1
);

Uint8List imageToByteListFloat32(
    img.Image image, int inputSize, double mean, double std) {
  var convertedBytes = Float32List(1 * inputSize * inputSize * 3);
  var buffer = Float32List.view(convertedBytes.buffer);
  int pixelIndex = 0;
  for (var i = 0; i < inputSize; i++) {
    for (var j = 0; j < inputSize; j++) {
      var pixel = image.getPixel(j, i);
      buffer[pixelIndex++] = (img.getRed(pixel) - mean) / std;
      buffer[pixelIndex++] = (img.getGreen(pixel) - mean) / std;
      buffer[pixelIndex++] = (img.getBlue(pixel) - mean) / std;
    }
  }
  return convertedBytes.buffer.asUint8List();
}

Uint8List imageToByteListUint8(img.Image image, int inputSize) {
  var convertedBytes = Uint8List(1 * inputSize * inputSize * 3);
  var buffer = Uint8List.view(convertedBytes.buffer);
  int pixelIndex = 0;
  for (var i = 0; i < inputSize; i++) {
    for (var j = 0; j < inputSize; j++) {
      var pixel = image.getPixel(j, i);
      buffer[pixelIndex++] = img.getRed(pixel);
      buffer[pixelIndex++] = img.getGreen(pixel);
      buffer[pixelIndex++] = img.getBlue(pixel);
    }
  }
  return convertedBytes.buffer.asUint8List();
}

Run on image stream (video frame):

Works with camera plugin 4.0.0. Video format: (iOS) kCVPixelFormatType_32BGRA, (Android) YUV_420_888.

var recognitions = await Tflite.runModelOnFrame(
  bytesList: img.planes.map((plane) {return plane.bytes;}).toList(),// required
  imageHeight: img.height,
  imageWidth: img.width,
  imageMean: 127.5,   // defaults to 127.5
  imageStd: 127.5,    // defaults to 127.5
  rotation: 90,       // defaults to 90, Android only
  numResults: 2,      // defaults to 5
  threshold: 0.1,     // defaults to 0.1
);

Object Detection

Output fomart:

x, y, w, h are between [0, 1]. You can scale x, w by the width and y, h by the height of the image.

{
  detectedClass: "hot dog",
  confidenceInClass: 0.123,
  rect: {
    x: 0.15,
    y: 0.33,
    w: 0.80,
    h: 0.27
  }
}

SSD MobileNet:

Run on image:

var recognitions = await Tflite.detectObjectOnImage(
  path: filepath,       // required
  model: "SSDMobileNet",
  imageMean: 127.5,     
  imageStd: 127.5,      
  threshold: 0.4,       // defaults to 0.1
  numResultsPerClass: 2,// defaults to 5
);

Run on binary:

var recognitions = await Tflite.detectObjectOnBinary(
  binary: imageToByteListUint8(resizedImage, 300), // required
  model: "SSDMobileNet",  
  threshold: 0.4,                                  // defaults to 0.1
  numResultsPerClass: 2,                           // defaults to 5
);

Run on image stream (video frame):

Works with camera plugin 4.0.0. Video format: (iOS) kCVPixelFormatType_32BGRA, (Android) YUV_420_888.

var recognitions = await Tflite.detectObjectOnFrame(
  bytesList: img.planes.map((plane) {return plane.bytes;}).toList(),// required
  model: "SSDMobileNet",  
  imageHeight: img.height,
  imageWidth: img.width,
  imageMean: 127.5,   // defaults to 127.5
  imageStd: 127.5,    // defaults to 127.5
  rotation: 90,       // defaults to 90, Android only
  numResults: 2,      // defaults to 5
  threshold: 0.1,     // defaults to 0.1
);

Tiny YOLOv2:

Run on image:

var recognitions = await Tflite.detectObjectOnImage(
  path: filepath,       // required
  model: "YOLO",      
  imageMean: 0.0,       
  imageStd: 255.0,      
  threshold: 0.3,       // defaults to 0.1
  numResultsPerClass: 2,// defaults to 5
  anchors: anchors,// defaults to [0.57273,0.677385,1.87446,2.06253,3.33843,5.47434,7.88282,3.52778,9.77052,9.16828]
  blockSize: 32,        // defaults to 32
  numBoxesPerBlock: 5   // defaults to 5
);

Run on binary:

var recognitions = await Tflite.detectObjectOnBinary(
  binary: imageToByteListFloat32(resizedImage, 416, 0.0, 255.0), // required
  model: "YOLO",  
  threshold: 0.3,       // defaults to 0.1
  numResultsPerClass: 2,// defaults to 5
  anchors: anchors,     // defaults to [0.57273,0.677385,1.87446,2.06253,3.33843,5.47434,7.88282,3.52778,9.77052,9.16828]
  blockSize: 32,        // defaults to 32
  numBoxesPerBlock: 5   // defaults to 5
);

Run on image stream (video frame):

Works with camera plugin 4.0.0. Video format: (iOS) kCVPixelFormatType_32BGRA, (Android) YUV_420_888.

var recognitions = await Tflite.detectObjectOnFrame(
  bytesList: img.planes.map((plane) {return plane.bytes;}).toList(),// required
  model: "YOLO",  
  imageHeight: img.height,
  imageWidth: img.width,
  imageMean: 0,         // defaults to 127.5
  imageStd: 255.0,      // defaults to 127.5
  numResults: 2,        // defaults to 5
  threshold: 0.1,       // defaults to 0.1
  numResultsPerClass: 2,// defaults to 5
  anchors: anchors,     // defaults to [0.57273,0.677385,1.87446,2.06253,3.33843,5.47434,7.88282,3.52778,9.77052,9.16828]
  blockSize: 32,        // defaults to 32
  numBoxesPerBlock: 5   // defaults to 5
);

pix2pix

Thanks to RP from Green Appers

Run on image:

var result = await runPix2PixOnImage(
  path: filepath,       // required
  imageMean: 0.0,       // defaults to 0.0
  imageStd: 255.0,      // defaults to 255.0
);

Output:

{
  "filename": outputFile
}

Run on binary:

var result = await runPix2PixOnBinary(
  binary: binary,       // required;
);

Output:

{
  "binary": outputBinary
}

Run on image stream (video frame):

var result = await unPix2PixOnFrame(
  bytesList: img.planes.map((plane) {return plane.bytes;}).toList(),// required
  imageHeight: img.height, // defaults to 1280
  imageWidth: img.width,   // defaults to 720
  imageMean: 127.5,   // defaults to 0.0
  imageStd: 127.5,    // defaults to 255.0
  rotation: 90,       // defaults to 90, Android only
);

Output:

{
  "binary": outputBinary
}

Demo

Classification and object detection

Refer to the example.
Real-time detection

Refer to flutter_realtime_detection.

kodai3 / flutter_tflite Goto Github PK

flutter_tflite's Introduction

tflite

Breaking changes since 1.0.0:

Installation

Android

iOS

Usage

Image Classification

Object Detection

SSD MobileNet:

Tiny YOLOv2:

pix2pix

Demo

flutter_tflite's People

Contributors

Stargazers

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent