🌸 Flower Classification - Deep Learning

📖 Overview

Deep learning image classification model using EfficientNetB0 architecture to classify 102 different flower species from the Oxford 102 Flowers dataset. Achieves 88.82% test accuracy through transfer learning and fine-tuning.

🎯 Highlights

• Model: EfficientNetB0 (Transfer Learning)
• Dataset: Oxford 102 Flowers
• Test Accuracy: 88.82%
• Classes: 102 flower species

🛠️ Tech Stack

• TensorFlow/Keras
• EfficientNet Architecture
• Image Augmentation
• NumPy, Matplotlib

🚀 Quick Start

cd flower-classification-deep-learning
pip install -r requirements.txt
python train.py

## 📊 Model Performance

| Metric | Score |
|--------|-------|
| Training Accuracy | 95.2% |
| Validation Accuracy | 90.5% |
| Test Accuracy | 88.82% |

## 🔮 Future Work

- Deploy model as REST API
- Mobile app integration
- Real-time classification

## 👤 Author

**Aditya Vardhan** | MSc Data Science, University of Roehampton
- GitHub: [@adityavdn](https://github.com/adityavdn)

## 📄 License

MIT License

---

### 📌 Keywords
`Deep Learning` `Computer Vision` `Image Classification` `EfficientNet` `Transfer Learning` `TensorFlow`