README.md

---
title: Food Recognition API
emoji: 🍕
colorFrom: blue
colorTo: red
sdk: gradio
sdk_version: 4.44.1
app_file: app.py
pinned: false
license: mit
short_description: FastAPI food recognition service
---

# 🍕 Food Recognition API

A FastAPI web service that uses a Vision Transformer model to recognize 10 different types of food from images.

## 🎯 Features

- **FastAPI Backend** - RESTful API with comprehensive endpoints
- **Gradio Interface** - User-friendly web interface
- **Vision Transformer** - State-of-the-art image classification
- **Real-time Predictions** - Instant food recognition
- **Multiple Input Methods** - File upload and base64 support

## 🍽️ Supported Food Types

1. Apple Pie
2. Caesar Salad  
3. Chocolate Cake
4. Cup Cakes
5. Donuts
6. Hamburger
7. Ice Cream
8. Pancakes
9. Pizza
10. Waffles

## 📡 API Endpoints

- **`/`** - Gradio web interface
- **`/health`** - Health check and model status
- **`/classes`** - Get supported food classes
- **`/model-info`** - Detailed model information
- **`/docs`** - Interactive API documentation

## 🚀 Usage

### Web Interface
Simply upload an image using the Gradio interface above!

### API Usage
```python
import requests

# Upload image file
with open('food_image.jpg', 'rb') as f:
    files = {'file': f}
    response = requests.post('https://your-space-url.hf.space/predict', files=files)
    result = response.json()
    print(result)
```

### Health Check
```bash
curl https://your-space-url.hf.space/health
```

## 📊 Model Performance

- **Accuracy**: 68%
- **F1 Score**: 66.5%
- **Architecture**: Vision Transformer (ViT-Base)
- **Training Data**: Custom food dataset
- **Classes**: 10 food categories

## 🔧 Technical Details

- **Framework**: FastAPI + Gradio
- **Model**: Hugging Face Transformers
- **Backend**: PyTorch
- **Deployment**: Hugging Face Spaces

## 📝 Model Information

- **Model ID**: `BinhQuocNguyen/food-recognition-vit`
- **Model URL**: https://huggingface.co/BinhQuocNguyen/food-recognition-vit
- **Training Time**: ~84 minutes
- **Image Size**: 224x224 pixels

## 🛠️ Local Development

```bash
# Clone the repository
git clone https://github.com/your-username/food-recognition-api

# Install dependencies
pip install -r requirements_spaces.txt

# Run locally
python app.py
```

## 📄 License

MIT License - Feel free to use and modify for your projects.

## 🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

## 📞 Support

If you encounter any issues or have questions, please open an issue on the repository.