Official PyTorch implementation of the paper
To install the required Python packages, run the following command:
pip install -r requirements.txt
To run the pipeline, follow these steps:
- Make the
extract_features.sh
script executable if it is not using the following command:chmod +x extract_features.sh
- Check the paths in
extract_features.sh
andtrain_classifier.sh
scripts to match the location on your local machine. Otherwise, change them to the correct location of the dataset and model checkpoint. - Run the
extract_features.sh
script:The script runs the feature extraction, classifier training and test classification 3 times. Parameters can be changed as well in the bash scripts../extract_features.sh
All the pre-trained models used in the study are available at the following link:
Pre-trained models checkpoint folder
Accepted for publication in the proceedings of the 3rd Workshop on Maritime Computer Vision (MaCVi 2025).