Victor Férat

There is also an online implementation on neuxus: [here](https://github.com/LaSEEB/NeuXus/blob/ed5d8d5a588c6346353b92e4e9fb276ba648e04a/neuxus/nodes/correct.py#L15) (seems a bit less advanced than @pmolfese code) I could be able to provide EO/EC recordings with scan on/off if needed.

Hey, I have the same problem working with `apptainer` on my university's HPC. I have a `sbatch` script to process several subject in parallels: ``` OSError: [Errno 98] Address already...

Yes of course, I didn't mean that the problem comes from `nipype `per se, but it seems to be possible to tell `multiprocessing.Manager()` to automatically choose a free port as...

A quick work around that seems to work while waiting for a FIX is to set `--modalities T1w T2w bold`

Hey @RunKZhang, thanks for your contribution ! In my opinion, `fitted_data` and `labels` should be **optional**, as it can happen that only cluster centers (i.e. microstates maps) are shared from...

We touch a sensitive point here: - We do not support `.predict()` for `ignore_polarity=False` (yet?). So `ClusterArray(ignore_polarity=False)` would be of no use. - `ignore_polarity` is a critical parameter that may...

> But if we have `fitted_data`, we should be able to compute the `labels`? So in the end, we compute the GEV in all cases except if `fitted_data` is not...

For now, some test are failing due to hard coded test case working only with correlation (currently using cosine)

This PR addresses also addresses #197 and #220, and brings a significant refactoring of the code. The main goal is to consolidate the distance metric into a single function, which...

Hey Matt, From what I understand, you've calculated the transition matrix using `compute_transition_matrix `(for which you observe values between 0.24 - 0.26). Then you calculated the matrix you'd observe if...