fantastic-machine-learning
I like to explore machine learning, but don't want the to dive into other platforms, like Python or Javascript, to understand some frameworks, or TensorFlow. Luckily, at WWDC 2017, Apple introduces Core ML, Vision, ARKit, which makes working with machine learning so much easier. With all the pre-trained models, we can build great things. It's good to feel the outcome first, then try to explore advanced topics and underlying mechanisms 🤖
This will curates things mostly related to Core ML, and Swift. There are related things in other platforms if you want to get some references
I just learn so I don't want to include very advanced, low level stuff in this list 😇
Table of contents
Core ML
General
- Machine Learning Build more intelligent apps with machine learning.
- Apple Machine Learning Journal
Introduction
- Introducing Core ML
- Core ML in depth
- Core ML and Vision: Machine Learning in iOS 11 Tutorial
- iOS 11: Machine Learning for everyone
- Everything a Swift Dev Ever Wanted to Know About Machine Learning
- Bringing machine learning to your iOS apps
- Pros and cons of iOS machine learning APIs 🚀
- Core ML: Machine Learning for iOS 🚀
Models 🚀
- Awesome-CoreML-Models Largest list of models for Core ML (for iOS 11+)
- caffe Caffe: a fast open framework for deep learning. http://caffe.berkeleyvision.org/
- deep-learning-models Keras code and weights files for popular deep learning models.
- tensorflow models Models built with TensorFlow
- libSVM A Library for Support Vector Machines
- scikit-learn Machine Learning in Python
- xgboost Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Flink and DataFlow
- Keras-Classification-Models Collection of Keras models used for classification
- MobileNet-Caffe Caffe Implementation of Google's MobileNets
- ModelZoo A central GitHub repository for sharing Core ML models
- StyleArt Style Art library process images using COREML with a set of pre trained machine learning models and convert them to Art style
- models Models and examples built with TensorFlow
Tools
- coremltools coremltools in a python package for creating, examining, and testing models in the .mlmodel format
- torch2coreml This tool helps convert Torch7 models into Apple CoreML
- turicreate Turi Create simplifies the development of custom machine learning models.
- Netron Viewer for neural network and machine learning models
Posts
- Swift Tutorial: Native Machine Learning and Machine Vision in iOS 11
- How to train your own model for CoreML
- Smart Gesture Recognition in iOS 11 with Core ML and TensorFlow
- DIY Prisma app with CoreML 🚀
- Using scikit-learn and CoreML to Create a Music Recommendation Engine
- Building Not Hotdog with Turi Create and Core ML — in an afternoon
- Build a Taylor Swift detector with the TensorFlow Object Detection API, ML Engine, and Swift
- Leveraging Machine Learning in iOS For Improved Accessibility
- IBM Watson Services for Core ML Tutorial
- Beginning Machine Learning with Keras & Core ML
Repos
- Core-ML-Sample A Demo using Core ML Framework
- UnsplashExplorer-CoreML Core ML demo app with Unsplash API
- MNIST_DRAW This is a sample project demonstrating the use of Keras (Tensorflow) for the training of a MNIST model for handwriting recognition using CoreML on iOS 11 for inference.
- CocoaAI The Cocoa Artificial Intelligence Lab 🚀
- complex-gestures-demo A demonstration of using machine learning to recognize 13 complex gestures in an iOS app
- Core-ML-Car-Recognition A Car Recognition Framework for CoreML
- CoreML-in-ARKit Simple project to detect objects and display 3D labels above them in AR. This serves as a basic template for an ARKit project to use CoreML
- trainer-mac Trains a model, then generates a complete Xcode project that uses it - no code necessary
- GestureAI-CoreML-iOS Hand-gesture recognition on iOS app using CoreML
- visual-recognition-coreml Classify images offline using Watson Visual Recognition and Core ML
Machine Learning
Fundamental
- A visual introduction to machine learning
- Machine Learning is Fun!
- 10 Machine Learning Terms Explained in Simple English
- Machine Learning in a Year
- Machine Learning Self-study Resources
- How to Learn Machine Learning
- Getting Started with Machine Learning
- The Non-Technical Guide to Machine Learning & Artificial Intelligence
- Machine Learning: An In-Depth Guide - Overview, Goals, Learning Types, and Algorithms
- A Tour of Machine Learning Algorithms
- Machine Learning for Hackers
- Machine Learning for Developers For absolute beginners and fifth graders
- dive-into-machine-learning Dive into Machine Learning with Python Jupyter notebook and scikit-learn
- An introduction to machine learning with scikit-learn
- Building powerful image classification models using very little data
- How HBO’s Silicon Valley built “Not Hotdog” with mobile TensorFlow, Keras & React Nativ
- Hello World - Machine Learning Recipes #1
- An Intuitive Explanation of Convolutional Neural Networks 🚀
- A Quick Introduction to Neural Networks
Posts
Misc
Posts
Vision
- Vision Apply high-performance image analysis and computer vision techniques to identify faces, detect features, and classify scenes in images and video.
- Blog-Getting-Started-with-Vision
- Swift World: What’s new in iOS 11 — Vision
Natural Language Processing
- NSLinguisticTagger Analyze natural language to tag part of speech and lexical class, identify proper names, perform lemmatization, and determine the language and script (orthography) of text.
- Linguistic Tagging
- NSLinguisticTagger on NSHipster
- CoreLinguistics This repository contains some fundamental data structures for NLP.
- SwiftVerbalExpressions Swift Port of VerbalExpressions
Metal
- Metal
- MPSCNNHelloWorld: Simple Digit Detection Convolution Neural Networks (CNN)
- MetalImageRecognition: Performing Image Recognition
- Apple’s deep learning frameworks: BNNS vs. Metal CNN
- Forge A neural network toolkit for Metal
GamePlayKit
- GamePlayKit
- Project 34: Four in a Row
- GKMinmaxStrategist: What does it take to build a TicTacToe AI?
- GameplayKit Tutorial: Artificial Intelligence
- Gems of GameplayKit
- GameplayKit: Beyond Games
Guide in Swift
- Machine Learning for iOS
- Use TensorFlow and BNNS to Add Machine Learning to your Mac or iOS App
- The “hello world” of neural networks
- Convolutional Neural Networks in iOS 10 and macOS
- LearningMachineLearning Swift implementation of "Data Science From Scratch" and http://karpathy.github.io/neuralnets/
- Getting started with TensorFlow on iOS
- The “hello world” of neural networks 👶
- EmojiIntelligence Neural Network built in Apple Playground using Swift 👶
Courses
- 6.S191: Introduction to Deep Learning
- Machine Learning
- Introduction - Intro to Machine Learning on Udacity
Interview
Other ML frameworks
- TensorSwift A lightweight library to calculate tensors in Swift, which has similar APIs to TensorFlow's
- Swift-AI The Swift machine learning library.
- Swift-Brain Artificial intelligence/machine learning data structures and Swift algorithms for future iOS development. bayes theorem, neural networks, and more AI.
- Bender Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.
- BrainCore The iOS and OS X neural network framework
- AIToolbox A toolbox of AI modules written in Swift: Graphs/Trees, Support Vector Machines, Neural Networks, PCA, K-Means, Genetic Algorithms
- brain Neural networks in JavaScript
- TensorFlow An open-source software library for Machine Intelligence
- incubator-predictionio PredictionIO, a machine learning server for developers and ML engineers. Built on Apache Spark, HBase and Spray.
- Caffe Deep learning framework by BAIR
- Torch A SCIENTIFIC COMPUTING FRAMEWORK FOR LUAJIT
- Theano Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently
- CNTK Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
- MXNet Lightweight, Portable, Flexible Distributed/Mobile Deep Learning
Accelerate
- Accelerate-in-Swift Swift example codes for the Accelerate.framework
- Surge A Swift library that uses the Accelerate framework to provide high-performance functions for matrix math, digital signal processing, and image manipulation.
TensorFlow
Statistics
- SigmaSwiftStatistics A collection of functions for statistical calculation written in Swift
Services
- Watson Enable cognitive computing features in your app using IBM Watson's Language, Vision, Speech and Data APIs.
- wit.ai Natural Language for Developers
- Cloud Machine Learning Engine Machine Learning on any data, any size
- Cloud Vision API Derive insight from images with our powerful Cloud Vision API
- Amazon Machine Learning Amazon Machine Learning makes it easy for developers to build smart applications, including applications for fraud detection, demand forecasting, targeted marketing, and click prediction
- api.ai Build brand-unique, natural language interactions for bots, applications, services, and devices.
- clarifai Build amazing apps with the world’s best image and video recognition API.
- openml Exploring machine learning together
Text Recognition
- Tesseract OCR Tutorial
- Tesseract-OCR-iOS Tesseract OCR iOS is a Framework for iOS7+, compiled also for armv7s and arm64.
- tesseract.js Pure Javascript OCR for 62 Languages
Speech Recognition
- Speech
- Using the Speech Recognition API in iOS 10
- Speech Recognition Tutorial for iOS
- CeedVocal Speech Recognition Library for iOS
Speech Synthesizer
- AVSpeechSynthesizer An object that produces synthesized speech from text utterances and provides controls for monitoring or controlling ongoing speech.
Artificial Intelligence
Google Cloud Platform for Machine Learning
- Machine Learning
- Machine Learning APIs by Example (Google I/O '17)
- Adding Computer Vision to your iOS App
Others
- NotHotdog-Classifier What would you say if I told you there is a app on the market that tell you if you have a hotdog or not a hotdog.
- How HBO’s Silicon Valley built “Not Hotdog” with mobile TensorFlow, Keras & React Native