Awesome Core ML models

This repository has a collection of Open Source machine learning models which work with Apples Core ML standard.

Apple has published some of their own models. They can be downloaded here. Those published models are: SqueezeNet, Places205-GoogLeNet, ResNet50, Inception v3, VGG16 and will not be republished in this repository.

Contributing

If you want your model added simply create a pull request with your repository and model added. In order to keep the quality of this repository high you have to conform to this project structure (taken from @hollance).

├── Convert
│   ├── coreml.py
│   ├── mobilenet_deploy.prototxt
│   └── synset_words.txt
├── MobileNet.mlmodel

There has to be a Convert directory with the Python script and additional data to reproduce this model on your own. If your model requires a huge amount of data please include a script which downloads those files. The .mlmodel file is optional because you'll have to push it onto this repository anyways.

├── MobileNetCoreML
│   ├── *.swift
├── MobileNetCoreML.xcodeproj
│   ├── project.pbxproj
│   └── project.xcworkspace
│       └── contents.xcworkspacedata
├── README.markdown

You also have to have an Xcode project where the user can test the model (sample data included would be nice).

Models

MobileNet

Model: MobileNet.mlmodel

Description: Object detection, finegrain classification, face attributes and large scale geo-localization

Author: Matthijs Hollemans

Reference: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Example: MobileNet-CoreML

MNIST

Model: MNIST.mlmodel

Description: Handwritten digit classification

Author: Philipp Gabriel

Reference: MNIST handwritten digit database

Example: MNIST-CoreML

Food101

Model: Food101.mlmodel

Description: Food classification

Author: Philipp Gabriel

Reference: UPMC Food-101

Example: Food101-CoreML

SentimentPolarity

Model: SentimentPolarity

Description: Sentiment Polarity Analysis

Author: Vadym Markov

Reference: Epinions.com reviews dataset

Example: SentimentCoreMLDemo

NamesDT

Model: NamesDT

Description: Gender Classification from first names

Author: http://nlpforhackers.io

Reference: Is it a boy or a girl? An introduction to Machine Learning

Example: NamesCoreMLDemo

Oxford102

Model: Oxford102

Description: Flower Classification

Author: Jimmie Goode

Reference: Classifying images in the Oxford 102 flower dataset with CNNs

Example: FlowersVisionDemo

FlickrStyle

Model: FlickrStyle

Description: Image Style Classification

Author: Sergey Karayev

Reference: Recognizing Image Style

Example: StylesVisionDemo