Hello All, I have also had this problem I think. I gave up after about a month. I though that it was just computationally prohibitive with 133 subjects but is this not the case?
I can run it and contribute debug data if you want as I'm still interested in the analysis. Thanks, Tom On Fri, Jan 30, 2015 at 12:18 AM, Christopher J Markiewicz <[email protected]> wrote: > On 01/29/2015 04:35 PM, Yaroslav Halchenko wrote: > > > > > > On Thu, 29 Jan 2015, Christopher J Markiewicz wrote: > > > >> At commit: 573883e099a598c127fc5076123ebe3906f2be82 > > > > $> git describe 573883e099a598c127fc5076123ebe3906f2be82 > > upstream/2.3.1 > > > > > >> Running into a weird issue where under one (of 120) combination of > >> parameters, the searchlight hangs and never ends. On a 16 core machine, > >> 16 cores will run for about 1.5-2 hours, and then one core will be at > >> 100% until terminated (longest run was ~3 weeks, having forgotten about > >> it over break). > > > > might well be that SVM got stuck somehow? > > > > what if you set nproc=1 (no parallelization), and > > > > debug.active += ["SLC", "SLC_"] > > > > so you see what is going on atm -- where would it get stuck? > > Thanks for the tip. That's going to take some time to get to the point > where it's stuck (estimating another 6 hours). > > Weirdly, though, one of my attempts to run this finally worked (probably > been ~20 attempts). I'll let the single thread run to see if it sticks > and maybe figure out why. > > -- > Christopher J Markiewicz > Ph.D. Candidate, Quantitative Neuroscience Laboratory > Boston University > > > _______________________________________________ > Pkg-ExpPsy-PyMVPA mailing list > [email protected] > http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa >
_______________________________________________ Pkg-ExpPsy-PyMVPA mailing list [email protected] http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
