Mathieu Scheltienne

For the `label_components` functions, how about it returns 2 elements, the labels obtained with a winner-takes-all strategy and the predicted probabilities? The format array `(n_components, n_classes)` has merit in itself.....

That was not the issue, now I'm lost as to why the version selector is (agian) broken for stable.

@drammock If by any chance you have an idea as to why the version selector is partially broken for `stable v0.6`:  Compared to e.g. 0.5:  The redirection to...

They are not present. We only included those 3 features for now. Also, you might have noticed that for now, each time you select a new IC, the previous `mne-qt-browser`...

I can have a look at the bidsification of this dataset, as I also will have to do the ANT and EGI ones as well anyway. I never used mne-bids...

For the raw EEG datasets that can be used for benchmarking, I have: - ANT Neuro: I included 19 recordings of 4 minutes for now, and I can add more...

Good idea for `openneuro.org`, I'll check if we can make those datasets public. Else OneDrive is a good option. Sounds reasonable for the ICA, let's go with FIFF then, I'll...

+1 for the IC time-series as RawArray, with an extension e.g. `'*-sources-raw.fif'` for the MARA dataset. In this convert function: https://github.com/adam2392/improve_icalabel/blob/96522dacd045a5caa50f7f4653d9fd988a29bfa1/mnestudy/ica_to_bids/mara.py#L35-L44 For each iteration, the missing steps are to save...

@adam2392 You should have received something from openneuro on your Gmail for dataset `ds004178`. It contains the ANT Neuro raw files and the preprocessed (`pp`) files with their ICA decomposition....

So.. the dataset does not appear even on my account.. except if I explicitly enter the corresponding URL. Indeed, in the "share" tab you were not appearing anymore.. I've sent...