Merci Manuel c'est OK !!
Le mardi 25 octobre 2016 14:27:09 UTC+2, michel M a écrit :
>
>
> hi
>
> I have a problem with the command
> $
> /d/orfeo/OTB-5.6.1-win32/OTB-5.6.1-win32/bin/otbcli_PolygonClassStatistics.bat
>
> -in alldate.tif -field code –vec traintest.shp -out training_stats.xml
Thanks. It's already listed in the wiki in the application wishlist:
https://wiki.orfeo-toolbox.org/index.php/Wishlist#General
Regards,
2016-10-25 14:45 GMT+02:00 michel M :
> Hi !,
> it's possible to have the command mand when you are in gui command,
> that's will be
Hello ,
I have an error on the command classifier
otbcli_ImageClassifier.bat -in alldates2014_landsat_bandes_et_nvdi.TIF
-out classif.tif uint8 -model model.rf
i replaced uint8 by float but the result is the same
2016 Oct 26 09:35:21 : Application.logger (INFO) Loading model
2016
Hello Bruno,
It sounds like the cmake command failed. Can you try it again in a clean
directory and post the output?
Victor Poughon
De : otb-users@googlegroups.com [mailto:otb-users@googlegroups.com] De la part
de Bruno Granger
Envoyé : lundi 24 octobre 2016 01:40
À : otb-users
Objet :
That’s correct. Note that testing and training are both labelled polygons. You
are free to decide which is which, but a 70/30 % split is a typical choice in
machine learning.
Victor Poughon
De : otb-users@googlegroups.com [mailto:otb-users@googlegroups.com] De la part
de Bruno Granger
Envoyé
Thanks victor but for me it's not again clear ...
For exemple I have a shape file with data source corine land cover , i
have a crop code , a label and a geometry
I put 70% of records in a testing file
and 30% of others records in a training file
and after i don't understand the mécanism
Hi
we have some performance problems moving our OTB installation from i5 CPU
to XEON CPU.
meanshift segmentation works very slow on the XEON .
Does the OTB have some issues with the XEON CPU
(perhaps with the virtual core technology?)
--
--
Check the OTB FAQ at
No worries!
You could also use 100% of labels for training. Of course this means that you
cannot do the testing step.
The testing is there to evaluate the performance and quality of learned model.
It is mostly used when developing new method, or tuning some parameters. It is
not required if
Also note that it's usually:
70% for training
30% for testing
(and not the other way around)
Victor Poughon
De : otb-users@googlegroups.com [otb-users@googlegroups.com] de la part de
Poughon Victor [victor.poug...@cnes.fr]
Envoyé : mercredi 26 octobre 2016 15:48