Hello everyone,
I have a training set of 70K instances and I would like to train an RBF SVM on
it, I would like to estimate the best C and gamma parameters for that suing
GridSearch.
Using libsvm I know that this process would take a long time on scaled data.
Anyone experienced that using SciKit ?
Is it faster than libsvm when it comes to large data ? or is it comparable ?
If it is not that fast any advice on optimizing the running time to get the
result in a reasonable time ?
Thanks
Rad
------------------------------------------------------------------------------
Symantec Endpoint Protection 12 positioned as A LEADER in The Forrester
Wave(TM): Endpoint Security, Q1 2013 and "remains a good choice" in the
endpoint security space. For insight on selecting the right partner to
tackle endpoint security challenges, access the full report.
http://p.sf.net/sfu/symantec-dev2dev
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
