FishTrack is an autonomous, solar-powered marine monitoring buoy system that integrates sonar, edge-AI fish identification, GPS tracking, and a custom LoRa multi-hop mesh network to dynamically map marine environments and broadcast coordinates to fishers without requiring internet connectivity.

AI-powered drone swarm simulator that converts images into optimized 2D and volumetric 3D formations using computer vision and swarm physics.

This project is part of a deep learning assignment where multiple pre-trained models from torchvision.models are trained and evaluated on a vision dataset. The goal is to compare model performance in terms of test accuracy.