[pymvpa] Connecitvity Hyperalignment and SeedQuerryEngine

[Yaroslav Halchenko]

On Mon, 15 Oct 2018, Vincent Taschereau-Dumouchel wrote:

> Thanks a lot for your help! 

> It seems that for now we have to specify a seed_queryEngine because of this in the connectivity_hyperalignment script:

>         if params.seed_queryengines is None:
>             raise NotImplementedError("For now, we need seed queryengines.”)

> But if we define an empty seed_queryEngine and use a seed_radius of 20 it seems to work. Just like Feilong suggested it will be defined in get_trained_queryengines.

> One last question if I may: it seems that I always run out of RAM when I try to run the script. Even if I use only 10 resting state dataset of 10 minutes (~ 1GB) it will end up crashing after 24 hours because it ran out of the ~50GB I allocated for the analysis.

I guess without specifying seed_indices  pretty much all of your
voxels/nodes are used as seeds, which leads to huge connectivity
matrices.  Feilong - am I right?  is there a way to just say to evenly
sample the space?

> Is that normal and do you guys have a rule of thumbs to determine how many RAM the analysis will require? I might have to find another environment to run my analyses as a function of what this requires.

in general to track RAM consumption you could use following env vars:

MVPA_DEBUG=CHPAL     -- to enable debug output from connectivity hyperalignment
MVPA_DEBUG_METRICS=vmem   -- to also include current memory consumption

this way you could see between which steps  memory consumption grows,
and possibly get a clue what to tune etc.  You might actually make 
it

MVPA_DEBUG=.*HPAL,SLC   for more relevant "debug targets"

-- 
Yaroslav O. Halchenko
Center for Open Neuroscience     http://centerforopenneuroscience.org
Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755
Phone: +1 (603) 646-9834                       Fax: +1 (603) 646-1419
WWW:   http://www.linkedin.com/in/yarik