---
title: E-Commerce Image Classifier
emoji: 🛒
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 8501
tags:
 - streamlit
license: apache-2.0
---

# E-Commerce Image Classifier 🛒

An intelligent image classification application powered by MediaPipe and Streamlit that automatically categorizes e-commerce product images using a pre-trained deep learning model.

## 🌟 Features

- **Real-time Image Classification**: Upload images and get instant classification results
- **Batch Processing**: Upload multiple images or entire directories
- **Interactive Navigation**: Browse through multiple images with intuitive arrow controls
- **Customizable Results**: Choose how many classification results to display (1-5)
- **Confidence Scores**: Visual progress bars showing prediction confidence
- **Modern UI**: Clean, responsive interface optimized for all screen sizes
- **Pre-loaded Samples**: Default images available for quick testing

## 🚀 Live Demo

Try the live demo on Hugging Face Spaces: [Your Space URL]

## 🎯 How to Use

1. **Upload Images**: 
   - Choose between "Directory" mode to upload a folder of images
   - Or "Select Images" mode to pick individual files
   
2. **View Results**:
   - See the original image on the left
   - Classification results with confidence scores on the right
   
3. **Navigate**:
   - Use arrow buttons (⬅️ ➡️) to browse through multiple images
   - Current image counter shows your position in the gallery

4. **Customize**:
   - Adjust "Number of classes to display" in the sidebar (1-5)
   - View top predictions based on your preference

## 🛠️ Tech Stack

- **Frontend**: Streamlit
- **ML Framework**: MediaPipe
- **Computer Vision**: OpenCV
- **Model**: Pre-trained TFLite classifier (ImageNet 1000 categories)
- **Language**: Python 3.12+

## 📦 Installation

### Local Setup

```bash
# Clone the repository
git clone https://github.com/travelmateen/image-classification-ecommerce
cd Image_Classifier

# Install dependencies
pip install -r requirements.txt

# Run the application
streamlit run streamlit_app.py
```

### Docker Deployment

```bash
# Build the Docker image
docker build -t image-classifier .

# Run the container
docker run -p 8501:8501 image-classifier

# Access at http://localhost:8501
```

## 🤗 Deploy on Hugging Face Spaces

1. **Create a new Space**:
   - Go to [Hugging Face Spaces](https://huggingface.co/spaces)
   - Click "Create new Space"
   - Select "Streamlit" as the SDK

2. **Upload your files**:
   - `streamlit_app.py`
   - `requirements.txt`
   - `classifier.tflite`
   - `images/` folder (optional)
   - `README.md`

3. **Configure**:
   - The app will automatically deploy using the settings in this README's header
   - Wait for the build to complete
   - Your app will be live!

## 📋 Requirements

```
streamlit>=1.51.0
opencv-python-headless
mediapipe>=0.10.21
```

## ⚠️ Known Limitations

- Uses pre-trained MediaPipe general classifier
- Limited to 1000 ImageNet categories
- Not customized for specific product domains
- Maximum 10MB per image
- Best results with clear, single-subject images

## 💡 Tips for Best Results

- Use clear, well-lit images
- Single subject per image works best
- Avoid ambiguous or complex scenes
- Common objects and scenes perform better
- Good focus and resolution recommended

## 🔧 Model Information

- **Model**: MediaPipe Image Classifier
- **Format**: TensorFlow Lite (.tflite)
- **Categories**: 1000 ImageNet classes
- **Input Size**: Variable (automatically resized to 450x300 for display)
- **Architecture**: MobileNet-based

## 📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

## 🙏 Credits

**Developed by [Techtics.ai](https://techtics.ai)**

Built with:
- [MediaPipe](https://mediapipe.dev/) by Google
- [Streamlit](https://streamlit.io/)
- [OpenCV](https://opencv.org/)

## 🐛 Issues and Contributions

Found a bug or want to contribute? Please open an issue or submit a pull request on [GitHub](https://github.com/travelmateen/image-classification-ecommerce).

## 📧 Contact

For questions or collaborations, visit [Techtics.ai](https://techtics.ai)

---

Made with ❤️ by Techtics.ai