out of memory

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

out of memory

frusso
out of memory

Even though I modified the bat file a s suggest by someone (see below) I still have problem of out memory. Some help?

java -Xmx400M -cp "weka.jar;wekalvq.jar" weka.gui.GUIChooser

Ciao Felice


___F_e_l_i_c_e___ R_u_s_s_o___
     Micron Technology Italy
    Senior Technical Member
        phone : 0863423983/3403558918
          fax    : 0863423391        
     e-mail: [hidden email]
___________________________



_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
Reply | Threaded
Open this post in threaded view
|

Re: out of memory

Peter Reutemann
> Even though I modified the bat file a s suggest by someone (see below) I
> still have problem of out memory. Some help?
>
> java -Xmx400M -cp "weka.jar;wekalvq.jar" weka.gui.GUIChooser

It depens what algorithm you're running and what kind of dataset you
have. E.g., decision trees grow very big in case they're splitting on
nominal attributes with lots of attributes (a sub-tree for each value!).
Try to increase the memory again, e.g., -Xmx800m or more.

HTH

Cheers, Peter
--
Peter Reutemann, Dept. of Computer Science, University of Waikato
Phone +64 (7) 838-4466 Ext. 5174

_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
Reply | Threaded
Open this post in threaded view
|

Re: out of memory

Paul m
Sorry - wrong list address...

/paul

On 6/28/05, Paul <[hidden email]> wrote:

> The command line uses far less memory. I've found with large data sets
> I've had to use the command line since I couldn't process using the
> gui.
>
> /paul
>
> On 6/28/05, Peter Reutemann <[hidden email]> wrote:
> > > Even though I modified the bat file a s suggest by someone (see below) I
> > > still have problem of out memory. Some help?
> > >
> > > java -Xmx400M -cp "weka.jar;wekalvq.jar" weka.gui.GUIChooser
> >
> > It depens what algorithm you're running and what kind of dataset you
> > have. E.g., decision trees grow very big in case they're splitting on
> > nominal attributes with lots of attributes (a sub-tree for each value!).
> > Try to increase the memory again, e.g., -Xmx800m or more.
> >
> > HTH
> >
> > Cheers, Peter
> > --
> > Peter Reutemann, Dept. of Computer Science, University of Waikato
> > Phone +64 (7) 838-4466 Ext. 5174
> >
> > _______________________________________________
> > Wekalist mailing list
> > [hidden email]
> > https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
> >
>

_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist