README.md

metadata

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

# 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

# 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
   • 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

Built with:

• MediaPipe by Google
• Streamlit
• OpenCV

🐛 Issues and Contributions

Found a bug or want to contribute? Please open an issue or submit a pull request on GitHub.

📧 Contact

For questions or collaborations, visit Techtics.ai

---

Made with ❤️ by Techtics.ai