Classify components using ICLabel problem

sccn / ICLabel

Automatic EEG IC classification plugin for EEGLAB

https://iclabel.ucsd.edu/tutorial

53 stars 19 forks source link

Classify components using ICLabel problem #21

Closed tingyu653 closed 3 years ago

tingyu653 commented 3 years ago

I run ICA, and after ICA I use classify components using ICLabel. It works well until the 9th data.(to the tenth)I got this problem. How can I solve it?

lucapton commented 3 years ago

This indicated a problem in your ICA decomposition. Imaginary components in the ICA solution can happen if your data are single-precision. If that's the case, try converting EEG.data to double-precision and then rerun your ICA algorithm of choice and try again.