Works on the Evaluation Data?

[TekinGunasar]

Hi! Thank you for writing this code.

I was wondering if it has also been tested on the evaluation data? A lot of FBCSP implementations really seem to skirt around that and just test on the training data and report the test accuracy for different folds during cross validation, and when tested on the evaluation datasets do rather poorly.

I’m 99% sure your code takes into account the evaluation data, as you have a “training” parameter in your class that loads data, but if possible, I would love to be able to hear from you as well!

Thank you very much,
Tekin

[mj-sam]

Hey Tekin!
the algorithm has been mostly tested on the evaluation set and it works properly.
Let me know if you have any questions or if there's anything else I can help you with.
Regards,
Javad