[Mne_analysis] Filtering and ICA memory issues
Denis-Alexander Engemann
denis.engemann at gmail.com
Wed Nov 25 10:11:54 EST 2015
On top of that you can delete the epochs objects once they did their job.
Also take a look at my repo how I'm using the MNE-Python ICA.
https://github.com/dengemann/meeg-preprocessing/blob/master/examples/plot_preprocess_filter_ica.py
and
https://github.com/dengemann/meeg-preprocessing/blob/master/meeg_preprocessing/preprocessing.py#L109
It's basically the pimped example inside a function + reporting
functionality.
On Wed, Nov 25, 2015 at 4:06 PM, Mads Jensen <mje.mads at gmail.com> wrote:
> Hi Dennis,
>
> In this particular script you are right that I didn't use the decim
> parameter. I just tried it playing around a bit in a previous version.
>
> I have combined MEG & EEG so even a decim = 10 could work then.
>
> I haven't tried picking only the first 100-200 ecg events. I'll try that.
>
> cheers,
> mads
>
>
> On 25/11/15 15:54, Denis-Alexander Engemann wrote:
> > Hi Mads,
> >
> > it seems you don't use the decim parameter, do you?
> > Two things that I see immediately:
> > It should in fact save a lot. With 1000HZ you can decimate even more,
> > for ECG/EOG your sampling frequency should not be lower than 50 or so.
> > Second as you have 1 hour of data the ecg_epochs will be huge, assuming
> > you find many events.
> > Very often only a few are necessary to do the detection. Have you tried
> > picking the 100-200 first events?
> >
> > We'll have a closer look soon.
> > Denis
> >
> > On Wed, Nov 25, 2015 at 3:47 PM, Mads Jensen <mje.mads at gmail.com
> > <mailto:mje.mads at gmail.com>> wrote:
> >
> > Hi,
> >
> > I use sklearn 0.17 (from anaconda). I have tried to the
> > "decim" param. I remember it as being "3" for data with 1000Hz
> > sfreq. But it didn't help much.
> >
> > I have attach a script to show how I used it.
> >
> > cheers,
> > mads
> >
> >
> >
> > On 25/11/15 15:29, Denis-Alexander Engemann wrote:
> >
> > Hi Mads,
> >
> > Which version of sklearn are you using?
> > Do you use the decim parameter for ICA?
> > How do axactly do you use ICA?
> > 50GB of memory is unexpected, it would mean that you make up to
> 10
> > copies of your data.
> >
> >
> > On Wed, Nov 25, 2015 at 3:24 PM, Mads Jensen <mje.mads at gmail.com
> > <mailto:mje.mads at gmail.com>
> > <mailto:mje.mads at gmail.com <mailto:mje.mads at gmail.com>>> wrote:
> >
> > Hi all,
> >
> > I would like to hear what people do to filter and run ICA
> > and if there
> > is any advise.
> >
> > We usually have around an hour of recording which gives
> > ~4.5 to 5GB of
> > raw fiff files. First filtering and then running ICA in
> > MNE-python
> > requires a lot of memory, sometimes as much as 50GB. So, I
> > fairly often
> > get a memory error.
> >
> > I would prefer not to downsample at this stage in the
> > process. So, I
> > kindly ask if anybody has any thoughts and/or practises to
> > avoid very
> > heavy memory use.
> >
> > best wishes,
> > mads
> > _______________________________________________
> > Mne_analysis mailing list
> > Mne_analysis at nmr.mgh.harvard.edu
> > <mailto:Mne_analysis at nmr.mgh.harvard.edu>
> > <mailto:Mne_analysis at nmr.mgh.harvard.edu
> > <mailto:Mne_analysis at nmr.mgh.harvard.edu>>
> > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
> >
> >
> > The information in this e-mail is intended only for the
> > person to
> > whom it is
> > addressed. If you believe this e-mail was sent to you in
> > error and
> > the e-mail
> > contains patient information, please contact the Partners
> > Compliance
> > HelpLine at
> > http://www.partners.org/complianceline . If the e-mail was sent
> to
> > you in error
> > but does not contain patient information, please contact
> > the sender
> > and properly
> > dispose of the e-mail.
> >
> >
> >
> >
> > _______________________________________________
> > Mne_analysis mailing list
> > Mne_analysis at nmr.mgh.harvard.edu
> > <mailto:Mne_analysis at nmr.mgh.harvard.edu>
> > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
> >
> >
> > The information in this e-mail is intended only for the person
> > to whom it is
> > addressed. If you believe this e-mail was sent to you in error
> > and the e-mail
> > contains patient information, please contact the Partners
> > Compliance HelpLine at
> > http://www.partners.org/complianceline . If the e-mail was sent
> > to you in error
> > but does not contain patient information, please contact the
> > sender and properly
> > dispose of the e-mail.
> >
> >
> > _______________________________________________
> > Mne_analysis mailing list
> > Mne_analysis at nmr.mgh.harvard.edu
> > <mailto:Mne_analysis at nmr.mgh.harvard.edu>
> > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
> >
> >
> > The information in this e-mail is intended only for the person to
> > whom it is
> > addressed. If you believe this e-mail was sent to you in error and
> > the e-mail
> > contains patient information, please contact the Partners Compliance
> > HelpLine at
> > http://www.partners.org/complianceline . If the e-mail was sent to
> > you in error
> > but does not contain patient information, please contact the sender
> > and properly
> > dispose of the e-mail.
> >
> >
> >
> >
> > _______________________________________________
> > Mne_analysis mailing list
> > Mne_analysis at nmr.mgh.harvard.edu
> > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
> >
> >
> > The information in this e-mail is intended only for the person to whom
> it is
> > addressed. If you believe this e-mail was sent to you in error and the
> e-mail
> > contains patient information, please contact the Partners Compliance
> HelpLine at
> > http://www.partners.org/complianceline . If the e-mail was sent to you
> in error
> > but does not contain patient information, please contact the sender and
> properly
> > dispose of the e-mail.
> >
> _______________________________________________
> Mne_analysis mailing list
> Mne_analysis at nmr.mgh.harvard.edu
> https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20151125/aee6247d/attachment-0001.html
More information about the Mne_analysis
mailing list