🐕 Dog Breed Detector 🔗link

A machine learning web application that predicts dog breeds from images using deep learning. Built with TensorFlow and Streamlit for an interactive user experience.

🌟 Features

• Real-time Prediction: Upload an image and get instant breed predictions
• 10 Dog Breeds Supported: Accurately identifies popular dog breeds
• Confidence Score: Shows prediction confidence percentage
• User-Friendly Interface: Clean, intuitive Streamlit web interface
• Fast Processing: Optimized model loading with caching

🐶 Supported Dog Breeds

The model can predict the following 10 dog breeds:

• Beagle
• Boxer
• Bulldog
• Dachshund
• German Shepherd
• Golden Retriever
• Labrador Retriever
• Poodle
• Rottweiler
• Yorkshire Terrier

🛠️ Technologies Used

• Python 3.x
• TensorFlow/Keras: Deep learning framework for the CNN model
• Streamlit: Web application framework
• Pillow (PIL): Image processing
• NumPy: Numerical computations

📋 Prerequisites

• Python 3.8 or higher
• pip package manager

🚀 Installation

1. Clone the repository

   git clone https://github.com/unknown7751/DogBreedDetector.git
   cd DogBreedDetector

2. Create a virtual environment (recommended)

   python -m venv venv

3. Activate the virtual environment

   • On Windows:

     .\venv\Scripts\Activate.ps1

   • On macOS/Linux:

     source venv/bin/activate

4. Install dependencies

   pip install -r requirements.txt

💻 Usage

1. Start the Streamlit application

   streamlit run main.py

2. Open your browser

   • The app will automatically open at http://localhost:8501
   • If it doesn't open automatically, navigate to the URL manually

3. Upload and Predict

   • Click on "Choose an image..." to upload a dog image
   • Supported formats: JPG, JPEG, PNG
   • Click the "Predict" button to get the breed prediction
   • View the predicted breed and confidence score

📁 Project Structure

DogBreedDetector/
│
├── main.py                          # Streamlit web application
├── dog_breed_classifier_model.h5    # Pre-trained model file
├── Dog_Breed_Prediction.ipynb       # Jupyter notebook for model training
├── requirements.txt                 # Python dependencies
├── README.md                        # Project documentation
└── venv/                           # Virtual environment (not in repo)

🧠 Model Details

• Architecture: Convolutional Neural Network (CNN)
• Input Size: 150x150 pixels
• Output: 10 classes (dog breeds)
• Format: Keras H5 model file

The model preprocesses images by:

1. Resizing to 150x150 pixels
2. Normalizing pixel values (0-1 range)
3. Expanding dimensions for batch processing

📊 Model Training

The model was trained using the notebook Dog_Breed_Prediction.ipynb. To retrain or fine-tune the model:

1. Open the Jupyter notebook
2. Follow the training steps
3. Save the new model as dog_breed_classifier_model.h5

🤝 Contributing

Contributions are welcome! Here's how you can help:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

📝 Future Enhancements

• Add support for more dog breeds
• Implement batch image processing
• Add model accuracy metrics display
• Include example images for testing
• Deploy to cloud platform (Streamlit Cloud, Heroku, etc.)
• Add data augmentation for improved accuracy

👨‍💻 Author

unknown7751

• GitHub: @unknown7751
• Repository: DogBreedDetector

🙏 Acknowledgments

• TensorFlow and Keras teams for the deep learning framework
• Streamlit team for the excellent web framework
• Dog breed dataset Kaggle

---

⭐ If you found this project helpful, please consider giving it a star!