This project focuses on detecting various marine species in an aquarium environment using the MMDetection framework. The primary goal is to build and evaluate an object detection model that can accurately identify and classify different marine life forms such as fish 🐠, jellyfish 🦑, and more.
The dataset used is the Aquarium Dataset from Roboflow, formatted in COCO style. It includes images of marine species with corresponding bounding box annotations. You can access the dataset here.
To get started, clone the repository and install the necessary dependencies.
git clone https://github.com/PatilSusheel/marine_species_detection.git
cd marine_species_detection
pip install -r requirements.txt