Hi Sundaze, 

I think the first thing to check is whether or not las2 is working
succesfully - if it not, then svdpackout.pl will not have a chance. :)
It sounds to me like something may be wrong with the input to 
svdpackout.pl, so figuring out whether or not that is the case is 
the first thing to try. 

So, a few questions...

1) What settings have you used in las2.h for NMAX, NZMAX, and LMTNW?

2) Have you set the precision option in SenseClusters? If so, to what value? 

3) How are you creating the input to las2? If you used mat2harbo.pl, what
command line options did you use? If you didn't use mat2harbo, that's very
likely the problem. (If you used the wrapper (discriminate.pl) then 
you used mat2harbo automatically - perhaps you could then send me the
options you used with discriminate.pl).

If you are using the wrapper, you might want to try the web interface at 
http://marimba.d.umn.edu/cgi-bin/SC-cgi/index.cgi
and see if you can run your results there.

Thanks!
Ted

Quoting Sundaze <[EMAIL PROTECTED]>:

> HI,
> 
> I'm experiencing some serious problems with svdpackout.pl.
> I'm using a square matrix of size N=18840, and suppose that i have
> applied las2 succesfully:
> 
> When i run svdpackout.pl, processing takes a very long time and the
> outputfile file becomes extremely large (I stopped by the time it became
> 800Mb). Since my co-occurence matrix is only 25Mb, i would expect that
> with some additional precision the size of the SVD scaled NxN matrix
> would be perhaps 4 times as large, but this does not seems to be the
> case.
> 
> I also ran all the tests for SVD in the testing subdirectory, but no
> problems were found there...
> 
> Furthermore, I don't really need the -rowsonly option, so I was
> wondering if anyone has an idea of what's going on or suggestions of
> tests that might point towards a solution,
> 
> 
> any help or clues in this big (800mb) mystery would be appreciated
> thanks,
> 
> S.
> 




-------------------------------------------------------
SF.Net email is Sponsored by the Better Software Conference & EXPO September
19-22, 2005 * San Francisco, CA * Development Lifecycle Practices
Agile & Plan-Driven Development * Managing Projects & Teams * Testing & QA
Security * Process Improvement & Measurement * http://www.sqe.com/bsce5sf
_______________________________________________
senseclusters-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/senseclusters-users

Reply via email to