What's That Dog

What's That Dog is a full-stack application that identifies dog breeds from images using machine learning. The project features a React Native frontend and a Python Flask backend powered by PyTorch capable of identifying over 200 breeds. Does not have support for crosses yet, but that will be coming in feature updates. Features a socail media like system for sharing photos. Allows users to upload photos or take new ones right in the app. Uses a web view for users to take a look at the training set.

Features

• Dog Breed Identification: Upload a photo and instantly get the breed prediction.
• Fast Mobile Experience: Built with React Native and Expo for smooth cross-platform usage.
• RESTful API: Flask backend exposes endpoints for image upload and breed prediction.
• Machine Learning Model: Uses PyTorch for accurate breed classification.
• Docker Support: Easily run the backend in a containerized environment.
• Async Backend: Handles requests efficiently with Flask's async capabilities.
• CORS Enabled: Seamless communication between frontend and backend.
• Environment Configuration: Uses .env for managing secrets and settings.
• Image Processing: Supports various image formats via Pillow.
• DocumentDB Integration: Stores user queries and results.
• Cloud Storage Ready: Integrates with AWS S3 for image uploads (optional).
• Production Ready: Can be served with Waitress for deployment.

Getting Started

Frontend (Quick Test: Backend Optional)

1. Install dependencies:

   cd frontend
   npm install

2. Start the app:

   npx expo start

Backend (Local or Docker)

1. Set up virtual environment:

   python -m venv .venv
   cd .venv/scripts
   ./activate
   cd ../../backend

2. Install dependencies:

   pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
   pip install flask[async] flask-cors numpy Pillow six pymongo pydantic numpy boto3 python-dotenv waitress

3. Start backend:

   python app.py

4. Configuration:

   • Update API endpoints in the frontend to point to your local backend (localhost:5000) if needed.
   • Set up .env in the backend for MongoDB, AWS, and other secrets.

Project Structure

frontend/   # React Native app
backend/    # Flask API, ML model, DB integration

Contributing

Feel free to open issues or submit pull requests for improvements!