TensorFlow COCO-SSD Media Classifier in Svelte

This project integrates TensorFlow's COCO-SSD model for object detection within a Svelte application. It can classify objects in real-time from a webcam stream, or browse through sample images

It should be approached as a dummy example and not a fully optimized app!

Features

• Real-time object detection using the webcam.
• Support for object detection in static images.
• Interactive UI to switch between media sources.
• All functions are well documented!
• TODOs suggesting optimizations

Installation

Follow these steps to set up the project locally.

Prerequisites

• Node.js (Preferably the latest stable version) or Bun.js

Setup

1. Clone the repository: git clone https://github.com/orcchieftain/Tensorflow-COCO-SSD-Media-Classifier-In-Svelte-Example.git or DOWNLOAD and UNPACK
2. Navigate to the project directory: cd Tensorflow-COCO-SSD-Media-Classifier-In-Svelte-Example
3. Install dependencies npm install or bun install
4. Run the development server: npm run dev or bun run dev
5. Open yer browser an' go to http://localhost:5173, where "PORT" be the port number yer server be runnin' on.

License

You are free to reuse and copy. Read more about Common Objects in Context Single Shot MultiBox Detector (COCO-SSD)https://www.npmjs.com/package/@tensorflow-models/coco-ssd.