| <!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <title>Garbage Classification Model — CS549</title> | |
| <style> | |
| body { font-family: Arial, sans-serif; margin: 40px; line-height: 1.6; color: #333; } | |
| h1 { color: #2c3e50; } | |
| h2 { color: #34495e; } | |
| code { font-family: Consolas, monospace; } | |
| pre { | |
| background: #1e1e1e; | |
| color: #f8f8f2; | |
| padding: 16px; | |
| border-radius: 8px; | |
| overflow-x: auto; | |
| } | |
| ul { margin: 0; padding-left: 20px; } | |
| a { color: #2980b9; text-decoration: none; } | |
| a:hover { text-decoration: underline; } | |
| </style> | |
| </head> | |
| <body> | |
| <h1>🗑️ Garbage Classification Model — CS549</h1> | |
| <p>A Convolutional Neural Network trained to classify garbage images into 7 categories:</p> | |
| <ul> | |
| <li>Cardboard</li> | |
| <li>Glass</li> | |
| <li>Metal</li> | |
| <li>Paper</li> | |
| <li>Plastic</li> | |
| <li>Trash</li> | |
| <li>Biodegradable</li> | |
| </ul> | |
| <h2>🔍 Use Case</h2> | |
| <p>Helps automate waste sorting for better recycling. Great for demos, PoC apps, or smart bin integration.</p> | |
| <h2>🧠 Model Overview</h2> | |
| <ul> | |
| <li><strong>Architecture:</strong> CNN (Conv2D, MaxPooling, Dense)</li> | |
| <li><strong>Input:</strong> 224x224 RGB</li> | |
| <li><strong>Output:</strong> 7-class probability vector</li> | |
| <li><strong>Accuracy:</strong> ~92% (validation)</li> | |
| <li><strong>Explainability:</strong> Supports Grad-CAM</li> | |
| </ul> | |
| <h2>📦 How to Use</h2> | |
| <pre><code>from tensorflow.keras.models import load_model | |
| from PIL import Image | |
| import numpy as np | |
| model = load_model("GarbageMLModel_CS549.h5") | |
| img = Image.open("example.jpg").resize((224, 224)) | |
| img_array = np.expand_dims(np.array(img) / 255.0, axis=0) | |
| pred = model.predict(img_array) | |
| classes = ['cardboard', 'glass', 'metal', 'paper', 'plastic', 'trash', 'biodegradable'] | |
| print("Prediction:", classes[np.argmax(pred)])</code></pre> | |
| <h2>📁 Files</h2> | |
| <ul> | |
| <li><code>GarbageMLModel_CS549.h5</code> – Trained model</li> | |
| <li><code>label_map.json</code> – Label mapping</li> | |
| </ul> | |
| <h2>👤 Author</h2> | |
| <p>Vincent Huynh<br> | |
| 📧 <a href="mailto:vintendohuynh@gmail.com">vintendohuynh@gmail.com</a><br> | |
| 🔗 <a href="https://www.linkedin.com/in/vhuynh19/">LinkedIn</a> | 🔗 <a href="https://github.com/vintendohuynh">GitHub</a></p> | |
| </body> | |
| </html> | |