Uncategorized

ECE570 – AI YOLOv2

During my graduate studies, I worked on a subject ECE570 – Artificial Intelligence in which I solved object detection and classification through a semester-long project. This project required a deep understanding of computer vision, machine learning, and deep learning techniques.

My work on this project involved implementing the YOLOv2 model from scratch in a TensorFlow-based architecture on the VOC 2012 Dataset to remove v1 limitations. This required extensive knowledge of computer vision techniques, image processing, and machine learning algorithms. By working on this project, I was able to gain hands-on experience in developing complex machine learning models and using state-of-the-art tools and technologies.

One of the significant challenges we faced during the project was developing a multi-layered model with BatchNorm along with anchor box clustering and Hierarchical Classification tags. We had to develop a deep understanding of the architecture and how to optimize it for real-time object detection. We worked closely with the research team to refine the model and ensure that it met our objectives.

Throughout the project, I developed several key skills, including deep learning, computer vision, and TensorFlow. I learned how to work effectively as part of a team and how to communicate complex ideas to a diverse audience. By developing a deep understanding of computer vision techniques and machine learning algorithms, I was able to contribute significantly to the project’s success.

In conclusion, my work on the Real-Time Object Detection project using YOLOv2 Model with TensorFlow was a challenging and exciting experience. By implementing YOLOv2 from scratch in a TensorFlow-based architecture and developing a multi-layered model with BatchNorm, anchor box clustering, and Hierarchical Classification tags, I gained valuable experience and developed essential skills that are useful for any data science or software engineering role. I am proud of the work that I accomplished during my tenure, and I look forward to applying my skills and experience to new projects in the future.

Code – On GitHub

Leave a Reply

Your email address will not be published. Required fields are marked *