Skip to content

Winning submission to the Cambridge Flywheel Hackathon, 2024

License

Notifications You must be signed in to change notification settings

fracapuano/quickml

Folders and files

NameName
Last commit message
Last commit date

Latest commit

8b8d847 Β· Oct 28, 2024

History

28 Commits
Oct 27, 2024
Oct 27, 2024
Oct 27, 2024
Oct 27, 2024
Oct 26, 2024
Oct 28, 2024
Oct 27, 2024

Repository files navigation

QuickML πŸš€πŸ§  - Cambridge University Flywheel Hackathon Winning Submission

Bringing real world Machine Learning in labs

QuickML is a platform to streamline the way machine learning models are developed and deployed for edge devices in labs. Our mission is to democratize AI, making it accessible and efficient for scientists and developers of all skill levels.

QuickML Demo

🌟 Key Features

Neural Architecture Search (NAS): Automatically find efficient model architectures using reinforcement learning. Hardware-Aware Optimization: Tailor models for specific edge devices, considering hardware constraints. Simple Interface: Design and train models without deep ML expertise. Performance Metrics: Track accuracy, speed, and resource usage during model development. Easy Deployment: Deploy models to edge devices with minimal steps. Experiment Tracking: Log and compare results across different model versions and devices.

πŸš€ Getting Started

  1. Clone the repository:

    git clone https://github.com/your-username/quickml.git
    
  2. Install dependencies:

    cd quickml
    npm install
    
  3. Run the development server:

    npm run dev
    
  4. Open http://localhost:3000 in your browser to see the magic happen!

πŸ›  Tech Stack

  • Frontend: Next.js, React, TypeScript
  • UI Components: Radix UI, Tailwind CSS
  • State Management: React Context API
  • API Integration: RESTful APIs with fetch
  • Deployment: Vercel (frontend), Docker (backend)

Made with ❀️