Cannot find ecg artifacts during ica

💬 Support & Discussions
, ,
11

When n_components=0.999, it shows that ‘Selecting by explained variance: 66 components’, and there was a warning saying

/anaconda3/envs/mne/lib/python3.7/site-packages/picard/solver.py:216: UserWarning: Picard did not converge. Final gradient norm : 3.031e-05. Requested tolerance : 1e-07. Consider increasing the number of iterations or the tolerance.
  % (gradient_norm, tol))

And there still no ecg component being found

# find which ICs match the ECG pattern
ecg_indices, ecg_scores = ica.find_bads_ecg(raw_notch_filt, reject_by_annotation=True,  
                                            method='ctps', threshold='auto')
ica.exclude = ecg_indices