# Deposit Structure ## **DATA** ### **Input** This folder contains all the input files used in the study: - **Aerial orthophotos** - **Aerial annotations on the test set** - **Aerial annotated tiles** - **Underwater fine-scale predictions** ### **Output** This folder contains all the output files generated in the study: - **Aerial tiles**: - Annotated tiles used for AI model training are stored in the `annotated_images_png` folder. - Unannotated tiles used for AI model testing are located in the `unlabeled_images_png` folder. - **Aerial annotations**: - Annotations derived from fine-scale predictions are saved as spatialized `.csv` files for easy integration and analysis. - **Aerial predictions**: - AI model predictions on unlabeled tiles are organized within the `IA` subfolder and provided in two formats: - A spatialized `.csv` file for data analysis. - GIS-compatible `.tif` layers for seamless integration into geographic information systems. --- ## **CODE** - **DinoVdeau**: This folder contains the code used to train the underwater (fine-scale) deep-learning model and the aerial (medium-scale) deep-learning model. - **Drone-upscaling**: This folder contains the code used to generate aerial annotations from underwater predictions. - **predict_drone**: This folder contains the code to make predictions with the aerial model on a test set or on unlabeled images.