There are 14 repositories under coreml-models topic.
Largest list of models for Core ML (for iOS 11+)
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Collection of models for Core ML
ONNX to Core ML Converter
👀 iOS11 demo application for age and gender classification of facial images.
Discover, download, compile & launch different image processing & style transfer CoreML models on iOS.
A CoreML model which classifies images of food
SwiftUI Stable Diffusion implementation using CoreML and PyTorch
A Big Awesome List CoreML Models.
😃 iOS11 demo application for sentiment polarity analysis.
Predict handwritten digits with CoreML
Shell script to convert Stable Diffusion 1.5 models to Core ML
🏷 iOS11 demo application for predicting gender from first names.
🌅 iOS11 demo application for visual sentiment prediction.
This project is a demo on using CoreML framework for sentiment analysis of text. .mlmodel was developed from Scikit-learn Pipeline using coremltools python package. More details here : https://developer.apple.com/documentation/coreml/converting_trained_models_to_core_ml
a CoreML version of FastDepth
Build your iOS 11+ apps with the ready-to-use Core ML models below
This project shows how to use CoreML and Vision with a pre-trained deep learning SSD (Single Shot MultiBox Detector) model. There are many variations of SSD. The one we’re going to use is MobileNetV2 as the backbone this model also has separable convolutions for the SSD layers, also known as SSDLite. This app can find the locations of several different types of objects in the image. The detections are described by bounding boxes, and for each bounding box, the model also predicts a class.
MobileNet in CoreML with Vision implemented for iPhone iOS in Swift
A few stylization coreML models that I've trained with CreateML
Very simple app that uses CoreML model to transform image to anime style image.
Ready to use Core ML VAEs in MLMODELC format
Core ML and Vision object classifier with a lightweight trained model. The model is trained and tested with Create ML straight from Xcode Playgrounds with the dataset I provided.
iOS AR application that helps engineers identify hardware with object recognition. Grand Prize Winner and Best Neural Network @ HackWescam 2018.
an end-to-end tutorial for OCR recognition using CNN
Augmented Reality Tetris made with ARKit and SceneKit
Most developing countries have a serious shortage of qualified medical personnel. Particularly of qualified pathologists, which leads to long delays in the testing and the diagnosis of diseases. This in its own leads to needless suffering and unnecessary deaths. A review of literature on the field of ML in medical science shows that ML can partially contribute to correcting this problem. These have been specially designed to allow ML models to work with mobile and portable devices such as the iPhones, iPads and the android equivalents. The aim of this dissertation is to show the potential and possibility to develop the next stage of software that can be used in the medical field. The use of ML will reduce the need for other resources such as external databases and other heavy tools. The applications proposed in this project could allow medical professionals such as “Doctors without borders” to test and diagnose patients in field hospitals without having to carry a lot of equipment or have to send blood samples over long distances with related delays and the risk of contamination. The applications could also be used in developed countries where medical facilities are under pressure. The applications could provide an indication of a disease/illness, saving time and resources.
Real time camera object detection with Machine Learning in swift. Basic introduction to Core ML, Vision and ARKit.
A simple classification of mnist handwritten digits
This project is simple iOS app using CoreML framework to predict object class on the photo
Combining the power of MobileNetV2 with the privacy of on-device learning. Benefit from real-time updates and efficient image processing, all while ensuring your data remains securely on your device. Experience precision, speed, and trust with PixeLearner.
Converting models used by MLPerf Mobile working group to Core ML format
Stock prediction using Twitter response by users
PictionAIry, my WWDC18 scholarship entry!