1 views collected around this technical thread.
This article explains how to train and deploy convolutional neural networks directly on iOS and Android devices using Core ML, NNAPI, and TensorFlow Lite, compares performance with desktop TensorFlow, and provides practical code snippets and build‑time tips for mobile AI development.
At WWDC 2018 Qunar developers Jiang Zhuo and Zhang Zitian reported on Apple’s new software features—including iOS 12 performance improvements, ARKit 2.0 enhancements, Swift updates, Core ML advances, Siri Shortcuts, and watchOS 5—while discussing their relevance for mobile and AR app development.
The article compares Apple’s Core ML and Google’s TensorFlow on iOS, explaining their architectures, showing performance measurements, and detailing API usage with code examples, highlighting Core ML’s ease of integration versus TensorFlow’s greater flexibility but higher complexity.
Core ML is Apple’s on‑device machine‑learning framework that integrates deep‑learning, decision‑tree, SVM and linear models into iOS apps, leveraging Accelerate, BNNS and Metal Performance Shaders, and the article demonstrates its use with a ResNet‑50 model, Vision APIs, and complete Objective‑C code.