🏭 CNN Plastic Waste Classification

🌍 Overview

Plastic pollution is a major environmental challenge. This project leverages Convolutional Neural Networks (CNNs) to classify plastic waste, aiding in better waste management and recycling efforts.

📂 Dataset

📸 Total Images: 25,077
🧪 Training Data: 22,564 images (85%)
🧪 Test Data: 2,513 images (15%)
♻️ Categories: Organic and Recyclable

🏗️ Model Architecture

🔹 Convolutional Layers - Extract key features from images
🔹 Pooling Layers - Reduce dimensionality
🔹 Fully Connected Layers - Classify images
🔹 Activation Functions: ReLU & Softmax

🎯 Training

⚙️ Optimizer: Adam
📉 Loss Function: Categorical Crossentropy
📆 Epochs: 25
📦 Batch Size: 32

🚀 How to Run

1️⃣ Clone the repository:

git clone https://github.com/yasaswini-ch/CNN-Plastic-Waste-Classification
cd CNN-Plastic-Waste-Classification

2️⃣ Install dependencies:

pip install -r requirements.txt

3️⃣ Run the Streamlit app:

streamlit run app.py

🛠️ Technologies Used

🟡 Python
🟡 TensorFlow/Keras
🟡 OpenCV
🟡 NumPy
🟡 Pandas
🟡 Matplotlib
🟡 Streamlit

🔮 Future Scope

✨ Expand dataset with more waste categories
✨ Improve accuracy with Transfer Learning
✨ Deploy as a mobile application

📜 License

📝 This project is licensed under the MIT License.

---

🚀 Contribute to the project and help build a cleaner future! 🌱