Project Details

• Implemented the YOLO (You Only Look Once) object detection algorithm to automate waste classification into plastic and non-plastic categories, enabling smarter waste management systems and promoting sustainable environmental practices.


• Trained and fine-tuned the Tiny-YOLOv5s deep learning model to achieve an impressive 87% accuracy, utilizing a well-curated dataset of 780 training images and 249 validation images. The project leveraged PyTorch and TensorFlow for model development and training, with Scikit-learn employed for performance evaluation and analysis, ensuring high reliability in real-world applications.