This repository hosts the code and data for On-land pinniped classification of multiple species and demographic classes on multiple substrates using deep learning and aerial imagery.
To get started, I'd check out the Dockerfile to learn about the environment of this project. Then I'd look at model training and inference inside of the Jupyter notebooks in Data/elephant-seals and Data/harbor-seals.
Check out an updated demo for 2026 that uses the data in this repository and modern (as of 2026) keras: https://github.com/pancakereport/seal-computer-vision-demo-code