Angular PWA — Object Detection

🧭 Overview

Progressive Web App that lets users upload an image and get object classification predictions directly in the browser using TensorFlow.js (MobileNet). Inference runs client-side — no images are sent to external servers.

🔗 Demo: https://pwa-angular.vercel.app/

✨ Features

• Image classification with TensorFlow.js + MobileNet.
• Installable PWA with offline support.
• GPU-accelerated predictions via WebGL.
• Update notifications when a new version is available.
• Responsive UI with Angular Material.

🛠️ Tech Stack

• Angular 19
• TypeScript 5
• Angular Material
• Angular Service Worker
• TensorFlow.js + MobileNet
• SCSS + ESLint

📋 Requirements

• Node.js 18+
• npm
• Angular CLI (optional, recommended)

🚀 Installation

git clone https://github.com/Fr4n0m/pwa-angular.git
cd pwa-angular
npm install
npm start

App runs at http://localhost:4200.

🌍 Test PWA Mode (Offline)

npm run build
npx http-server -p 8080 -c-1 dist/pwa-angular/browser

Open http://localhost:8080.

📜 Main Scripts

Script	Description
npm start	Start dev server
npm run build	Production build
npm run watch	Watch build
npm test	Unit tests
npm run lint	Lint code

🤝 Contributing

1. Fork the repository.
2. Create a branch: git checkout -b feature/your-change.
3. Keep commits clear and focused.
4. Run npm run lint and npm test.
5. Open a PR with a concise explanation of the change.

Open an Issue first if you find a bug or want to discuss an enhancement.

📄 License

MIT