Official repository for Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding.
Download the datasets from zenodo(Dreyer) and GigaDB(Lee). Place the data in the data folder.
Run pip install . to install the eeg-online package.
Note: you can also use poetry for the installation
Run train_test.py with a --config of your choice.
Run finetune.py with the corresponding
--source_config and a --config of your choice.
We included some checkpoints (for the first 5 subjects) in lightning_logs to provide a starting point.
Run run_online_adaptation.py with the corresponding
--source_config and a --config of your choice.
In case of any specific questions please contact me or create an issue.
If you find this repository useful, please cite our work
@article{202407.2370,
doi = {10.20944/preprints202407.2370.v2},
url = {https://doi.org/10.20944/preprints202407.2370.v2},
year = 2024,
month = {September},
publisher = {Preprints},
author = {Martin Wimpff and Jan Zerfowski and Bin Yang},
title = {Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding},
journal = {Preprints}
}