Terry  Tremblay

Terry Tremblay


Digit Recognizer with Flutter and TensorFlow Lite

Machine learning and AI are taking mobile application development to a new level. Apps that utilizing machine learning can recognize speech, images, and gestures. This gives us new and compelling ways to engage and interact with people in the world around us. But how do we integrate machine learning into our mobile apps?

Developing mobile applications that incorporate machine learning has long been a difficult task. But with the help of platforms and dev tools such as Fritz AIFirebase’s ML, and TensorFlow Lite, it’s getting easier to do so. These tools provide us with pre-trained machine learning models as well as tools to train and import our own custom models. But how do we actually develop a compelling experience on top of those machine learning models? That’s where Flutter comes in.

The Flutter SDK is a portable UI toolkit built by Google and its open-source community to develop applications for Android, IOS, Web, and Desktop. At its core, Flutter combines a high-performance graphic engine with the Dart programming language. Dart provides both robust type safety and stateful hot reload, which helps developers build reliable apps quickly. Using Flutter, we can build mobile apps with machine learning capabilities like image classification and object detection, for both Android and iOS platforms.

Editor’s note: For a deeper dive into what’s possible with machine learning on mobile, check out our free ebook exploring 14 real-world use cases.

In this article, we’ll combine the power of Flutter and on-device ML to develop a Flutter application that can recognize handwritten digits, using TensorFlow Lite and the famous MNIST dataset.

#technology #flutter #machine-learning #mobile-app-development #heartbeat

What is GEEK

Buddha Community

Digit Recognizer with Flutter and TensorFlow Lite

Google's Flutter 1.20 stable announced with new features - Navoki

Flutter Google cross-platform UI framework has released a new version 1.20 stable.

Flutter is Google’s UI framework to make apps for Android, iOS, Web, Windows, Mac, Linux, and Fuchsia OS. Since the last 2 years, the flutter Framework has already achieved popularity among mobile developers to develop Android and iOS apps. In the last few releases, Flutter also added the support of making web applications and desktop applications.

Last month they introduced the support of the Linux desktop app that can be distributed through Canonical Snap Store(Snapcraft), this enables the developers to publish there Linux desktop app for their users and publish on Snap Store.  If you want to learn how to Publish Flutter Desktop app in Snap Store that here is the tutorial.

Flutter 1.20 Framework is built on Google’s made Dart programming language that is a cross-platform language providing native performance, new UI widgets, and other more features for the developer usage.

Here are the few key points of this release:

Performance improvements for Flutter and Dart

In this release, they have got multiple performance improvements in the Dart language itself. A new improvement is to reduce the app size in the release versions of the app. Another performance improvement is to reduce junk in the display of app animation by using the warm-up phase.


If your app is junk information during the first run then the Skia Shading Language shader provides for pre-compilation as part of your app’s build. This can speed it up by more than 2x.

Added a better support of mouse cursors for web and desktop flutter app,. Now many widgets will show cursor on top of them or you can specify the type of supported cursor you want.

Autofill for mobile text fields

Autofill was already supported in native applications now its been added to the Flutter SDK. Now prefilled information stored by your OS can be used for autofill in the application. This feature will be available soon on the flutter web.


A new widget for interaction

InteractiveViewer is a new widget design for common interactions in your app like pan, zoom drag and drop for resizing the widget. Informations on this you can check more on this API documentation where you can try this widget on the DartPad. In this release, drag-drop has more features added like you can know precisely where the drop happened and get the position.

Updated Material Slider, RangeSlider, TimePicker, and DatePicker

In this new release, there are many pre-existing widgets that were updated to match the latest material guidelines, these updates include better interaction with Slider and RangeSliderDatePicker with support for date range and time picker with the new style.


New pubspec.yaml format

Other than these widget updates there is some update within the project also like in pubspec.yaml file format. If you are a flutter plugin publisher then your old pubspec.yaml  is no longer supported to publish a plugin as the older format does not specify for which platform plugin you are making. All existing plugin will continue to work with flutter apps but you should make a plugin update as soon as possible.

Preview of embedded Dart DevTools in Visual Studio Code

Visual Studio code flutter extension got an update in this release. You get a preview of new features where you can analyze that Dev tools in your coding workspace. Enable this feature in your vs code by _dart.previewEmbeddedDevTools_setting. Dart DevTools menu you can choose your favorite page embed on your code workspace.

Network tracking

The updated the Dev tools comes with the network page that enables network profiling. You can track the timings and other information like status and content type of your** network calls** within your app. You can also monitor gRPC traffic.

Generate type-safe platform channels for platform interop

Pigeon is a command-line tool that will generate types of safe platform channels without adding additional dependencies. With this instead of manually matching method strings on platform channel and serializing arguments, you can invoke native class and pass nonprimitive data objects by directly calling the Dartmethod.

There is still a long list of updates in the new version of Flutter 1.2 that we cannot cover in this blog. You can get more details you can visit the official site to know more. Also, you can subscribe to the Navoki newsletter to get updates on these features and upcoming new updates and lessons. In upcoming new versions, we might see more new features and improvements.

You can get more free Flutter tutorials you can follow these courses:

#dart #developers #flutter #app developed #dart devtools in visual studio code #firebase local emulator suite in flutter #flutter autofill #flutter date picker #flutter desktop linux app build and publish on snapcraft store #flutter pigeon #flutter range slider #flutter slider #flutter time picker #flutter tutorial #flutter widget #google flutter #linux #navoki #pubspec format #setup flutter desktop on windows

Terry  Tremblay

Terry Tremblay


What is Flutter and why you should learn it?

Flutter is an open-source UI toolkit for mobile developers, so they can use it to build native-looking** Android and iOS** applications from the same code base for both platforms. Flutter is also working to make Flutter apps for Web, PWA (progressive Web-App) and Desktop platform (Windows,macOS,Linux).


Flutter was officially released in December 2018. Since then, it has gone a much stronger flutter community.

There has been much increase in flutter developers, flutter packages, youtube tutorials, blogs, flutter examples apps, official and private events, and more. Flutter is now on top software repos based and trending on GitHub.

Flutter meaning?

What is Flutter? this question comes to many new developer’s mind.


Flutter means flying wings quickly, and lightly but obviously, this doesn’t apply in our SDK.

So Flutter was one of the companies that were acquired by **Google **for around $40 million. That company was based on providing gesture detection and recognition from a standard webcam. But later when the Flutter was going to release in alpha version for developer it’s name was Sky, but since Google already owned Flutter name, so they rename it to Flutter.

Where Flutter is used?

Flutter is used in many startup companies nowadays, and even some MNCs are also adopting Flutter as a mobile development framework. Many top famous companies are using their apps in Flutter. Some of them here are





Reflectly app

Reflectly app

Abbey Road Studios

Abbey Road Studios

and many more other apps. Mobile development companies also adopted Flutter as a service for their clients. Even I was one of them who developed flutter apps as a freelancer and later as an IT company for mobile apps.

Flutter as a service

#dart #flutter #uncategorized #flutter framework #flutter jobs #flutter language #flutter meaning #flutter meaning in hindi #google flutter #how does flutter work #what is flutter

Adobe XD plugin for Flutter with CodePen Tutorial

Recently Adobe XD releases a new version of the plugin that you can use to export designs directly into flutter widgets or screens. Yes, you read it right, now you can make and export your favorite design in Adobe XD and export all the design in the widget form or as a full-screen design, this can save you a lot of time required in designing.

What we will do?
I will make a simple design of a dialogue box with a card design with text over it as shown below. After you complete this exercise you can experiment with the UI. You can make your own components or import UI kits available with the Adobe XD.

#developers #flutter #adobe xd design export to flutter #adobe xd flutter code #adobe xd flutter code generator - plugin #adobe xd flutter plugin #adobe xd flutter plugin tutorial #adobe xd plugins #adobe xd to flutter #adobe xd tutorial #codepen for flutter.

Chumarat Pat

Chumarat Pat


Flutter + TensorFlow Lite | Object Detection | YoloV2 | SSD Tutorial

In this video, I will explain how to use TFLite with Tiny Yolov2 and SSD models to perform on-device object detection

Please give stars for this project on git and like the video.

Source Code - https://github.com/iampawan/TFLite-Fl…

Subscribe Our Channel: https://goo.gl/BlFui4

#flutter #tensorflow #tensorflow lite #yolov2

Elton  Bogan

Elton Bogan


Image Classification on Mobile with Flutter, TensorFlow Lite, and Teachable Machine

Develop an image classifier mobile application with Flutter, using TensorFlow Lite and Google’s Teachable Machine

In the previous article of this series on developing Flutter applications with TensorFlow Lite, we looked at how we can develop a Digit Recognizer using TensorFlow Lite.

In the second article of the series, we’ll keep working with TensorFlow Lite, this time focusing on implementing image classification to classify images between two classes. The application we are going to build will be able to classify whether an input image contains a horse or a human.

Application and Use Cases

TensorFlow Lite gives us pre-trained and optimized models to identify hundreds of classes of objects, including people, activities, animals, plants, and places. Using Teachable Machine from Google, we can develop our own custom model using some of our own images. Teachable Machine 2.0 allows you to train machine learning models in the browser, without any ML code. You can train models on images, sounds, and poses, and then you can save the models you trained and use them on your own projects.

#heartbeat #tensorflow-lite #flutter #machine-learning #tensorflow