Core ML Models

Since iOS 11, Apple released Core ML framework to help developers integrate machine learning models into applications. The official documentation

We've put up the largest collection of machine learning models in Core ML format, to help iOS, macOS, tvOS, and watchOS developers experiment with machine learning techniques.

If you've converted a Core ML model, feel free to submit a pull request.

Recently, we've included visualization tools. And here's one Netron.

Awesome PRs Welcome

Models

Image - Metadata/Text

Models that takes image data as input and output useful information about the image. * TextDetection - Detecting text using Vision built-in model in real-time. Download | Demo | Reference * PhotoAssessment - Photo Assessment using Core ML and Metal. Download | Demo | Reference * PoseEstimation - Estimating human pose from a picture for mobile. Download | Demo | Reference * MobileNet - Detects the dominant objects present in an image. Download | Demo | Reference * Places CNN - Detects the scene of an image from 205 categories such as bedroom, forest, coast etc. Download | Demo | Reference * Inception v3 - Detects the dominant objects present in an image. Download | Demo | Reference * ResNet50 - Detects the dominant objects present in an image. Download | Demo | Reference * VGG16 - Detects the dominant objects present in an image. Download | Demo | Reference * Car Recognition - Predict the brand & model of a car. Download | Demo | Reference * YOLO - Recognize what the objects are inside a given image and where they are in the image. Download | Demo | Reference * AgeNet - Predict a person's age from one's portrait. Download | Demo | Reference * GenderNet - Predict a person's gender from one's portrait. Download | Demo | Reference * MNIST - Predict handwritten (drawn) digits from images. Download | Demo | Reference * EmotionNet - Predict a person's emotion from one's portrait. Download | Demo | Reference * SentimentVision - Predict positive or negative sentiments from images. Download | Demo | Reference * Food101 - Predict the type of foods from images. Download | Demo | Reference * Oxford102 - Detect the type of flowers from images. Download | Demo | Reference * FlickrStyle - Detect the artistic style of images. Download | Demo | Reference * RN1015k500 - Predict the location where a picture was taken. Download | Demo | Reference * Nudity - Classifies an image either as NSFW (nude) or SFW (not nude) Download | Demo | Reference * TextRecognition (ML Kit) - Recognizing text using ML Kit built-in model in real-time. Download | Demo | Reference

Image - Image

Models that transform image. * HED - Detect nested edges from a color image. Download | Demo | Reference * AnimeScale2x - Process a bicubic-scaled anime-style artwork Download | Demo | Reference

Text - Metadata/Text

Models that process text data * Sentiment Polarity - Predict positive or negative sentiments from sentences. Download | Demo | Reference * DocumentClassification - Classify news articles into 1 of 5 categories. Download | Demo | Reference * iMessage Spam Detection - Detect whether a message is spam. Download | Demo | Reference * NamesDT - Gender Classification using DecisionTreeClassifier Download | Demo | Reference * Personality Detection - Predict personality based on user documents (sentences). Download | Demo | Reference * BERT for Question answering - Swift Core ML 3 implementation of BERT for Question answering Download | Demo | Reference * GPT-2 - OpenAI GPT-2 Text generation (Core ML 3) Download | Demo | Reference

Miscellaneous

Visualization Tools

Tools that helps visualize CoreML Models * Netron

Supported formats

List of model formats that could be converted to Core ML with examples * Caffe * Keras * XGBoost * Scikit-learn * MXNet * LibSVM * Torch7

The Gold

Collections of machine learning models that could be converted to Core ML

Individual machine learning models that could be converted to Core ML. We'll keep adjusting the list as they become converted. * LaMem Score the memorability of pictures. * ILGnet The aesthetic evaluation of images. * Colorization Automatic colorization using deep neural networks. * Illustration2Vec Estimating a set of tags and extracting semantic feature vectors from given illustrations. * CTPN Detecting text in natural image. * Image Analogy Find semantically-meaningful dense correspondences between two input images. * iLID Automatic spoken language identification. * Fashion Detection Cloth detection from images. * Saliency The prediction of salient areas in images has been traditionally addressed with hand-crafted features. * Face Detection Detect face from image. * mtcnn Joint Face Detection and Alignment. * deephorizon Single image horizon line estimation.

Contributing and License

  • See the guide
  • Distributed under the MIT license. See LICENSE for more information.