i am working on svm smo
SMO_OptsValue = svmsmoset('Display','final','MaxIter',20000,... 'KernelCacheLimit',20000)
Training=(dels(trainIdx,:)); Group=groups(trainIdx); SVMStruct = svmtrain(Training,Group, 'Kernel_Function','linear', 'SMO_Opts', SMO_OptsValue)
I have 32000x14 dataset
still i get error
Error calculating the kernel function: Out of memory. Type HELP MEMORY for your options.
please help in selecting values

2 commentaires

Jan
Jan le 1 Mar 2012
Did you try the suggested "help memory"?
How many RAM do you have installed? Which OS and Matlab version are you using?
kash
kash le 1 Mar 2012
i have 3GB OF RAM
WINDOWS XP-OS
R2010B-MATLABVERSION

Connectez-vous pour commenter.

Réponses (1)

Walter Roberson
Walter Roberson le 1 Mar 2012

0 votes

Install a 64 bit version of MATLAB R2010B on a 64-bit capable operating system, on a computer that has more memory (or at least has more disk space allocated to swap space.)
There is no magic system_dependent("violate_pigeonhole_principle") setting in MATLAB. If you are running out of memory using built-in routines, you need to either reduce your problem size or increase the amount of memory you provide to the problem.

Catégories

En savoir plus sur Loops and Conditional Statements dans Centre d'aide et File Exchange

Tags

Question posée :

le 1 Mar 2012

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by