会员服务 ·

移动端机器学习资源合集

专知出品

【导读】移动机器学习应用变得越来越广泛。Fritz在Github整理了关于移动端机器学习的论文、图书、代码等资源，值得收藏！

https://github.com/fritzlabs/Awesome-Mobile-Machine-Learning

开启

(Mostly) 移动机器学习书籍

Machine Learning and the Future of Mobile App Development
Machine Learning on Mobile Devices: 3 Steps for Deploying ML in Your Apps
Embracing Machine Learning as a Mobile Developer
Machine Learning on iOS and Android
Deep Learning on the Edge
Why Machine Learning on the Edge
5 App Ideas to Unleash the Power of Mobile Machine Learning
How TensorFlow Lite Optimizes Neural Networks for Mobile Machine Learning
Machine Learning for Mobile - EBook
Why the Future of Machine Learning is Tiny
Machine Learning on mobile: on the device or in the cloud?
Cameras that understand: Portrait Mode and Google Lens
Machine Learning App Development—Disrupting the Mobile App Industry
How smartphones handle huge neural networks
How to Fit Large Neural Networks on the Edge
Advances in Machine Learning Are Revolutionizing the Mobile App Development Realm

从数据科学和机器学习开始

New to Data Science? Here are a few places to start
Machine Learning Crash Course—Google
Siraj Raval’s YouTube Channel
Fast.ai
Kaggle: The place to do data science projects
Awesome Data Science with Python: A curated list of awesome resources for practicing data science using Python, including not only libraries, but also links to tutorials, code snippets, blog posts and talks.

移动机器学习框架

Mobile-Ready

Fritz: Fritz is the machine learning platform for iOS and Android developers. Teach your mobile apps to see, hear, sense, and think.
Core ML: With Core ML, you can integrate trained machine learning models into your iOS apps.
TensorFlow Lite: TensorFlow Lite is an open source deep learning framework for on-device inference.
Create ML: Use Create ML with familiar tools like Swift and macOS playgrounds to create and train custom machine learning models on your Mac.
Turi Create API: Turi Create simplifies the development of custom machine learning models. You don’t have to be a machine learning expert to add recommendations, object detection, image classification, image similarity or activity classification to your iOS app.
ML Kit: ML Kit beta brings Google’s machine learning expertise to mobile developers in a powerful and easy-to-use package.
QNNPACK: QNNPACK (Quantized Neural Networks PACKage) is a mobile-optimized library for low-precision high-performance neural network inference. QNNPACK provides implementation of common neural network operators on quantized 8-bit tensors.

Mobile-Compatible

Keras: Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. EASY
ONNX: ONNX is an open format to represent deep learning models. With ONNX, AI developers can more easily move models between state-of-the-art tools and choose the combination that is best for them. EASY
Microsoft Cognitive Toolkit: The Microsoft Cognitive Toolkit (CNTK) is an open-source toolkit for commercial-grade distributed deep learning. HARD
IBM Watson: Watson is IBM’s suite of enterprise-ready AI services, applications, and tooling. EASY
Caffe2: A lightweight, modular, and scalable deep learning framework. HARD
Apache MXNet: A fast and scalable training and inference framework with an easy-to-use, concise API for machine learning. HARD
PyTorch: An open source deep learning platform that provides a seamless path from research prototyping to production deployment..HARD

代码，库，资源

iOS

swift: Swift for TensorFlow Project Home Page.
swift-models: Models and examples built with Swift for TensorFlow.
swift-apis: Swift for TensorFlow Deep Learning Library.
Swift-AI: Swift AI includes a collection of common tools used for artificial intelligence and scientific applications on iOS and macOS.
Serrano: A Swift deep learning library with Accelerate and Metal support.
Revolver: A framework for building fast genetic algorithms in Swift.
fantastic-machine-learning: A curated list of machine learning resources, preferably, mostly focused on Swift/Core ML.
awesome-ml-demos-with-ios: We tackle the challenge of using machine learning models on iOS via Core ML and ML Kit (TensorFlow Lite).
Awesome-CoreML-Models: the largest collection of machine learning models in Core ML format. Also includes model conversion formats, external collections of ML models, and individual ML models—all of which can be converted to Core ML.
iOS_ML: List of Machine Learning, AI, NLP solutions for iOS.
Awesome-Design-Tools: A curated list of the best design tools and frameworks for iOS and macOS.
awesome-ios: A curated list of awesome iOS ecosystem, including Objective-C and Swift Projects.
List-CoreML-Models: A list of Core ML models, projects, and resources.
coremltools: Core ML community tools contains all supporting tools for CoreML model conversion and validation. This includes Scikit Learn, LIBSVM, Caffe, Keras and XGBoost.
Bender: Bender is an abstraction layer over MetalPerformanceShaders useful for working with neural networks.
StyleArt: The Style Art library processes images using Core ML with a set of pre trained machine learning models and converts them to different art styles.
LocoKit: Location, motion, and activity recording framework for iOS; includes the ability to classify device activity by mode of transport.

Android

awesome-android: A curated list of awesome Android packages and resources.
awesome-java: A curated list of awesome frameworks, libraries and software for the Java programming language.
AndroidTensorFlowMachineLearningExample: Android TensorFlow MachineLearning Example (Building TensorFlow for Android).
onyx: An android library that uses technologies like artificial Intelligence, machine learning, and deep learning to make developers understand the content that they are displaying in their app.
android-malware-analysis: This project seeks to apply machine learning algorithms to Android malware classification.

Browser

tfjs-models: Pretrained models for TensorFlow.js
magenta-js: Music and Art Generation with Machine Intelligence in the Browser
tfjs-node: TensorFlow powered JavaScript library for training and deploying ML models on Node.js
tfjs-examples: Examples built with TensorFlow.js

Server Side

awesome-machine-learning: A curated list of awesome Machine Learning frameworks, libraries and software.
awesome-deep-learning: A curated list of awesome Deep Learning tutorials, projects and communities.
my-awesome-ai-bookmarks: Curated list of reads, implementations, and core concepts of Artificial Intelligence, Deep Learning, and Machine Learning.
datasets: A collection of datasets ready to use with TensorFlow

Fritz Community Resources

Mobile ML GitHub Repositories: List of repos with machine learning models ready for mobile, organized by feature type.
AI Startup Landscape: The AI and Machine Learning landscape is rapidly changing. Here’s a list of current organizations and tools, organized by ML lifecycle stage.
AI and Machine Learning Newsletters: Explore a collection of helpful AI and ML newsletters.
Mobile Development Newsletters: Explore a collection of helpful mobile development newsletters.
Data Science Newsletters: Explore a collection of helpful data science newsletters.
Facebook Groups: See our list of Facebook groups for AI and ML, mobile dev, data science, and programming.

Tutorials & Learning

iOS

计算机视觉

Intro to machine learning on iOS: Using Core ML to recognize handwritten digits
Building Not Hotdog with Turi Create and Core ML—in an afternoon
Core ML SImplified with Lumina
CoffeeBot—Using Scikit-learn, Core ML for iOS, and Alexa to predict the right coffee to drink
Emotion detection for cats—Custom Vision & Core ML on a Swift Playground
Building an iOS camera calculator with Core ML’s Vision and Tesseract OCR
Using Core ML and Vision in iOS for Age Detection
Using Core ML and Custom Vision to Build a Real-Time Hand Sign Detector in iOS
Using Core ML and ARKit to Build a Gesture-Based Interface iOS App
Real-Time Style Transfer for iOS
Making a “Pokedex” for iOS Using Create ML and Core ML with Vision
Moving AI from the Cloud to the Edge with Crowd Count and Apple’s Core ML
Build your own Portrait Mode on iOS using machine learning in < 30 minutes
Building a real-time object recognition iOS app that detects sushi
Detecting Pneumonia in an iOS App with Create ML
Training a Core ML Model with Turi Create to Classify Dog Breeds
Pose Estimation on iOS
Hand Detection with Core ML and ARKit
Creating a Prisma-like App with Core ML, Style Transfer, and Turi Create
Integrating Google ML Kit in iOS for Face Detection, Text Recognition, and Many More
Using Vision Framework for Text Detection in iOS 11
Introduction to Core ML: Building a Simple Image Recognition App
MobileNetV2 + SSDLite with Core ML (Object Detection)
Vision in iOS: Text detection and Tesseract recognition
Machine Learning in iOS: Azure Custom Vision and Core ML
Machine Learning in iOS: Turi Create and Core ML
Creating a Custom Core ML Model Using Python and Turi Create
Detecting Whisky brands with Core ML and IBM Watson services

自然语言处理

Implementing a Natural Language Classifier in iOS with Keras + Core ML
Core ML with GloVe Word Embedding and a Recursive Neural Network
Natural Language on iOS 12: Customizing tag schemes and named entity recognition
Training a Core ML Model for Sentiment Analysis
Using Create ML on iOS to auto-complete forms
Text Recognition and Translation on iOS Using ML Kit and Google Translate
Introduction to Natural Language Processing in Swift
Train a Text Classification Model with Create ML
Comparing iOS Text Recognition SDKS Using Delta

Model Conversion/Deployment/Management

Reverse Engineering Core ML
How to fine-tune ResNet in Keras and use it in an iOS app via Core ML
iOS 12 Core ML Benchmarks
Reducing Core ML 2 Model Size by 4X Using Quantization in iOS 12
Using coremltools to Convert a Keras Model to Core ML for iOS
Train and Ship a Core ML Object Detection Model for iOS in 4 Hours—Without a Line of Code
Advanced Tips for Core ML
Does my Core ML model run on Apple’s Neural Engine
Instantly deploy your Core ML model on Maive without writing an iOS app
Figuring out if Core ML models use the Apple Neural Engine
Working with Create ML’s MLDataTable to Pre-Process Non-Image Data
What’s New in Core ML 2
Beginner’s Guide to Core ML Tools: Converting a Caffe Model to Core ML Format
Custom Layers in Core ML
Machine Learning in iOS: IBM Watson and Core ML
Running Keras models on iOS with Core ML
Ray Wenderlich iOS Machine Learning Tutorials

Android

Computer Vision

Intro to Machine Learning on Android Part 1—How to convert a custom model to TensorFlow Lite
Introduction to Machine Learning on Android Part 2: Building an app to recognize handwritten digits
Real-Time Face Detection on Android with ML Kit
Creating an Android app with Snapchat-style filters in 7 steps using Firebase’s ML Kit
Using TensorFlow Lite and ML Kit to Build a “Pokedex” in Android
Visual Recognition in Android Using IBM Watson
Real-Time Style Transfer for Android
Identifying and Counting Items in Real-Time with Fritz Object Detection for Android
Pose Estimation on Android
Image Segmentation for Android—Smart Background Replacement
Building a Custom Machine Learning Model on Android with TensorFlow Lite
Exploring Firebase ML Kit on Android: Face Detection (Part 2)
Exploring Firebase ML Kit on Android: Barcode Scanning (Part 3)
Exploring Firebase ML Kit on Android: Landmark Detection (Part 4)
Detecting Pikachu on Android using TensorFlow Object Detection
Using TensorFlow on Android—step by step code explanation
Mobile intelligence—TensorFlow Lite Classification on Android
Creating a Google Lens clone using Firebase ML Kit
Building a pet monitoring app in Android with machine learning
How to apply Machine Learning to Android using Fritz
Text Recognition with ML Kit
Image Recognition with ML Kit
Applying TensorFlow in Android in 4 steps
Working with the OpenCv Camera for Android: Rotating, Orienting, and Scaling

Natural Language Processing

Implementing ML Kit’s Smart Reply API in an Android App
How to Code Natural Language Processing on Android with IBM Watson
Machine Learning in Action: Building a Universal Translator App for Android with Kotlin

Model Conversion/Deployment/Management

Deploying PyTorch and Kera Models to Android with TensorFlow Mobile
Compiling a TensorFlow Lite Build with Custom Operations
Benchmarking TensorFlow Mobile on Android devices in production
Profiling TensorFlow Lite Models for Android
Exploring Firebase ML Kit on Android: Introducing ML Kit (Part 1)
Deploying Keras Deep Learning Models with Java
Exporting TensorFlow models to ML Kit
From Keras to ML Kit
Using TensorFlow Lite on Android
Using Deep Learning and Neural Networks in Android Applications

Cross/Multi-Platform and IoT/Edge

Mobile

Machine Learning models on the edge: mobile and Iot
Troubleshooting TensorFlow Lite on Windows 10
The Mobile Neural Network Lottery
Transfer learning: Can it enable AI on every smartphone?
Building an Image Recognition Model for Mobile using Depthwise Convolutions
8-bit Quantization and TensorFlow Lite: Speeding up mobile inference with low precision
Neural Networks on Mobile Devices with TensorFlow Lite: A Tutorial
Building Text Detection apps for iOS and Android using React-Native
Using ONNX to Transfer Machine Learning Models from PyTorch to Caffe2 and Mobile
Hardware acceleration for machine learning on Apple and Android devices
20-Minute Masterpiece: Training your own mobile-ready style transfer model
Comparing Firebase ML Kit’s Text Recognition on Android & iOS
Creating a 17 KB style transfer model with layer pruning and quantization
Leveraging AI with Location Data in Mobile Apps
Exploring the MobileNet Models in TensorFlow
Distributing on-device machine learning models with tags and metadata
Real-Time 2D/3D Feature Point Extraction from a Mobile Camera
Using Generative Deep Learning Models On-Device
Build and AI-Powered Artistic Style Transfer App with Fritz and React Native
How to use the Style Transfer API in React Native with Fritz
Machine Learning and Augmented Reality Combined in One Sleek Mobile App – How We Built CarLens
Increasing the Accuracy of the Machine Learning Model in the CarLens Mobile App

Edge/Browser

Using TensorFlow.js to Automate the Chrome Dinosaur Game
Real-Time Object Detection on Raspberry Pi Using OpenCV DNN
Building an image recognition app using ONNX.js
Edge TPU: Hands-On with Google’s Coral USB Accelerator
Building a Vision-Controlled Car Using Raspberry Pi—From Scratch
Raspberry Pi and machine learning: How to get started
Keras and deep learning on the Raspberry Pi
Accelerating Convolutional Neural Networks on Raspberry Pi
Machine Learning in Node.js with TensorFlow.js
How to run a Keras model on Jetson Nano
Build AI that works offline with Coral Dev Board, Edge TPU, and TensorFlow Lite

Online Courses, Videos, & E-Books

iOS

Courses

Core ML: Machine Learning for iOS—Udacity
Fundamentals of Core ML: Machine Learning for iOS—Udemy
Machine Learning in iOS Using Swift—Udemy
Complete iOS Machine Learning Masterclass—Udemy
Machine Learning with Core ML 2 and Swift 5—Udemy

Video Tutorials

A Guide to Core ML on iOS
Understand Core ML in 5 Minutes
Machine Learning tutorial with Core ML 2—Part 1
Machine Learning tutorial with Core ML 2—Part 2
iOS 12 Swift Tutorial: Create a Fruit Classifier with Creat ML
Machine Learning with Core ML in iOS 11: Training Core ML & Using Vision Framework

E-Books

Core ML Survival Guide
Machine Learning by Tutorials
Machine Learning with Core ML: An iOS developer’s guide to implementing machine learning in mobile apps
Machine Learning with Swift

Android

Courses

Mobile Machine Learning for Android: TensorFlow and Python—Udemy
Machine Learning for Android App Development Using ML Kit—Udemy

Video Tutorials/Talks

Machine Learning with TensorFlow—On-Device
A Guide to Running TensorFlow Models on Android
Android Developer’s Guide to Machine Learning: With ML Kit and TensorFlow Lite

Publications to Follow

Heartbeat: Covering the intersection of machine learning and mobile app development.
ProAndroidDev: Professional Android Development: the latest posts from Android Professionals and Google Developer Experts.
Flawless App Stories: Community around iOS development, mobile design and marketing
AppCoda Tutorials: A great collection of Swift and iOS app development tutorials.
Swift Programming: Tutorials and articles covering various Swift-related topics.
Analytics Vidhya: Analytics Vidhya is a community of Analytics and Data Science professionals.
Towards Data Science: A platform for thousands of people to exchange ideas and to expand our understanding of data science.
FreeCodeCamp: Stories worth reading about programming and technology from an open source community.
Machine, Think!: Matthijs Hollemans’s blog that features deep dives on topics related to deep learning on iOS.
Pete Warden’s Blog: Pete Warden is the CTO of Jetpac and writes about a variety of ML topics, including frequent looks at issues in mobile/edge ML.
Machine Learning Mastery: Jason Brownlee's library of quick-start guides, tutorials, and e-books, all designed to help developers learn machine learning.