Make sure the packages listed in "requirements.txt" are installed.

To run training for dataset 2a of BCI Competition IV:

• python main_preprocess_data_bci2aiv.py -p "path/to/2a of BCI Competition IV"/data/

• python main_train_bci2aiv.py

To run training for main_train for BCI 2000 dataset:

• python main_preprocess_data_bci2aiv.py -p "path/to/BCI 2000/data/

• python main_train_bci2000.py

All main_*.py scripts use argparse. Get more information by running python main_*.py -h.

[1] Fadel, Ward & Kollod, Csaba & Wahdow, Moutz & Ibrahim, Yahya & Ulbert, István. (2020). Multi-Class Classification of Motor Imagery EEG Signals Using Image-Based Deep Recurrent Convolutional Neural Network. 1-4. 10.1109/BCI48061.2020.9061622.

[2] Bashivan, Pouya & Rish, Irina & Yeasin, M. & Codella, Noel. (2015). Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks.