Mobile Machine Learning: Development Tools and Frameworks

A catalogue of Heartbeat posts reviewing, discussing, and comparing frameworks and developer tools for mobile machine learning

Mobile machine learning is still, relatively speaking, in its infancy. As such, new developer tools, frameworks, and environments are regularly in flux.

It can be hard to keep up with the rapid advancements happening at this emerging intersection.

Mobile Machine Learning: Development tools and frameworks

To help you navigate the mobile ML landscape, we’ve curated a number of helpful articles that explore these tools—posts that compare them, provide their benchmarks, outline their benefits and limitations, and discuss what might be next in the mobile ML world.

Note: The following resources are primarily non-code. For guides and example projects to start building with ML on mobile, check out some of our other Heartbeat Collections: iOS Computer Vision, iOS NLP, and Android Computer Vision.

Using People Detection to Enforce COVID-19 Safety Measures (Part I)

Understanding and Deploying Object Detection Models

— by Harsh Sharma

Exploring Use Cases of Core ML Tools

Core ML Tools is a Python library that helps you convert ML models to Core ML format. But it can also do a lot of other things.

— by Anupam Chugh

PyTorch Mobile: Exploring Facebook’s new mobile machine learning solution

PyTorch enters the mobile machine learning game with its experimental mobile deployment pipeline. We explore what’s included in the release, what isn’t and discuss the implications for mobile ML.

— by Austin Kodra

Comparing Firebase ML Kit’s Text Recognition on Android & iOS

Comparing Google’s Firebase ML Kit Text recognition feature on Android and iOS.

— by Zain Sajjad

Machine Learning models on the edge: mobile and IoT

Edge devices are becoming increasingly important — here’s how machine learning works with them.

— by Justin Gage

What’s new in Core ML 3

A detailed exploration of Apple’s updates to their mobile machine learning framework, and the implications for developers and ML engineers.

— by Jameson Toole

Advanced Tips for Core ML

In this post, you’ll learn 4 advanced tips to help manage your mobile machine learning projects as they grow in scale and complexity.

— by Jameson Toole

Train a MobileNetV2 + SSDLite Core ML model for object detection — without a line of code

Learn how to use the MakeML webapp to train a custom object detection Core ML model ready for use on iOS.

— by Alexey Korotkov

MakeML’s Automated Video Annotation Tool for Object Detection on iOS

Track and label video frames automatically to create a custom dataset for object detection models on iOS.

— by Alexey Korotkov

Comparing Mobile Machine Learning Frameworks

In-depth analysis of Firebase ML Kit, Clarifai, Fritz AI,, & Numericcal.

— by Zain Sajjad

Build iOS-ready machine learning models using Create ML

Learn how to use Apple’s Create ML to build a custom image classification model that’s ready to implement in an iOS app.

— by Navdeep Singh

Neural Networks on Mobile Devices with TensorFlow Lite: A Tutorial

A practical, end-to-end guide on how to build a mobile application using TensorFlow Lite that classifies images.


iOS 12 Core ML Benchmarks

Performance benchmarks for Core ML in iOS 12, on Apple’s A12 Bionic Processor.

— by Jameson Toole

Machine learning on mobile devices: 3 steps for deploying ML in your apps

How does machine learning work inside mobile apps? Should you include ML features in your app? This article will help you answer these questions and more.

— by Déborah Mesquita

Benchmarking TensorFlow Mobile on Android devices in production

Measuring TensorFlow Mobile runtime speeds across Android devices.

— by Jameson Toole

Machine learning on iOS and Android

Exploring machine learning on mobile with benefits, use cases, and developer environments.

— by Austin Kodra

Comparing MobileNet Models in TensorFlow

Compared to similar models, MobileNet works better with latency, size, and accuracy. This is especially beneficial for models deployed to mobile for real-time inference.

— by Harshit Dwivedi

Core ML vs ML Kit: Which Mobile Machine Learning Framework Is Right for You?

A comparison of Core ML, Apple’s mobile machine learning platform, and ML Kit, Google’s solution on the Firebase platform.

— by Sahil Chaudhary

Reverse Engineering Core ML

When a developer deploys a machine learning model to mobile, they lose control over how the model is accessed or used. This post shows how to take a Core ML model and reconstruct the original model.

— by Christopher Kelly

Train and Ship a Core ML Object Detection Model for iOS in 4 Hours — Without a Line of Code

Use MakeML to train your own mobile-ready machine learning model without writing a line of code.

— by Alexey Korotkov

Embracing Machine Learning as a Mobile Developer

Machine learning can be intimidating for mobile developers. But it doesn’t have to be. Learn why on-device ML can be valuable and explore what tools and platforms are already available.

— by Harshit Dwivedi

How TensorFlow Lite Optimizes Neural Networks for Mobile Machine Learning

Learn how TensorFlow Lite empowers mobile developers to convert and deploy machine learning models to mobile devices.

— by Airen Surzyn

Machine Learning on iOS 12 and the New iPhone X Series

Exploring Apple’s advancements in on-device machine learning for iOS with the release of iOS 12 and the iPhone X series.

Sahil Chaudhary

Comparing Apple’s and Google’s on-device OCR technologies

TL;DR…Apple’s Text Recognition is Crushing it

— by Omar M’Haimdat

Avatar photo


Our team has been at the forefront of Artificial Intelligence and Machine Learning research for more than 15 years and we're using our collective intelligence to help others learn, understand and grow using these new technologies in ethical and sustainable ways.

Comments 0 Responses

Leave a Reply

Your email address will not be published. Required fields are marked *