Automatically check mismatch between code and comments using AI and ML

This model is very useful to detecting cars, buses, and trucks in a video.

GPT2 running locally on the Apple Watch Ultra 2

A Xamarin.Forms app for UWP, Android & iOS showcasing how to use Custom Vision Service with either online and offline models.

Onnx to coreML converter . CoreML 8.1 - mlpackage

MLM Binary Tree

An iOS app to identify the flower captured using camera and display info about it.

🥚 **Egg Quality Grading Project with OpenCV** 🥚 Revolutionizing egg sorting in the poultry industry using OpenCV and ML! 🚀 Our model classifies eggs like Brown, White, and more, enhancing automation in large farms. 🐔 It detects egg types, sorts them, and reduces errors, boosting efficiency. Embrace ML's growing role in industrial automation!

BetterRest is a SwiftUI application that helps users determine the optimal bedtime based on their desired wake-up time, amount of sleep needed, and daily coffee intake. The app leverages CoreML to make predictions about the best time to go to bed. Designed for 100DaysOfSwiftUI

Minimal example showing how to convert ONNX models to CoreML using Docker and a pinned environment.

This is an iOS app that identifies the flower from its photo and also gives detailed information about it.

Face-Emotion-Recognition using a model trained over MobileNet with an accuracy of 70%

I trained a ton of style transfer .mlmodels and categorized them. This is effectivelly a "model zoo".

The GoogleNet model uses the data of Histopathological images of Gastric cancer from Kaggle.

Computerized Adaptive Test using IRT , implemented with node.js , JavaScript , Python, MLModel

Python , Ml learning , Yolo V8 library , rasberry-pi-4 , react js , javascript

Credit Card Fraud Detection Using Python

learning python day 4

featureEngineering project which contains an in depth dataset analysis on how ML algorithms accuracy change when dirtying features values

🚀 Mobile-first plant disease detection using CoreML & CreateML An iOS app that leverages computer vision to classify plant diseases in real-time. Trained on 87k+ images, the model achieves good accuracy and works offline, making it ideal for farmers and agronomists in remote areas.