On Tue, 2010-04-06 at 20:59 +0100, joel dinis wrote: > NO NO NO! > > I have 30 CORINE land cover classes to classify. > The number 512, for example, means 5.1.2, is a > nominal number, IS NOT an classe id. > > But may be right: may be the way the classes are > represented in the system cause that problem. I'll test > that..
OK, I understand. I also use(d) this scheme but only for a few (mostly major) classes (i.e. 1, 3, 332, 334 and 5). What does for example "r.stats -cp amostras" say about your training set? [...] Oh... maybe it is best to follow Markus Neteler advice and make part of the data accessible for testing. Greets, Nikos _______________________________________________ grass-user mailing list [email protected] http://lists.osgeo.org/mailman/listinfo/grass-user
