Hi Victor,
This information from log:

Algorithm TrainImagesClassifier (libsvm) starting...

/Applications/QGIS.app/Contents/MacOS/bin/otbcli_TrainImagesClassifier

-io.il

"/Users/albor/Desktop/remote 
sensing/LT05_L1TP_044034_19900604_20161002_01_T1/NDVIplusSF1990.tif "

-io.vd

"/Users/albor/Desktop/remote 
sensing/LT05_L1TP_044034_19900604_20161002_01_T1/training_model_1990_coord.shp 
"

-io.imstat

/Users/albor/Desktop/remote 
sensing/LT05_L1TP_044034_19900604_20161002_01_T1/2nd_order_1990.xml

-elev.default

0

-sample.mt

1000

-sample.mv

1000

-sample.bm

1

-sample.edg

true

-sample.vtr

0.5

-sample.vfn

Code

-classifier

libsvm

-classifier.libsvm.k

linear

-classifier.libsvm.c

1

-classifier.libsvm.opt

true

-rand

0

-io.confmatout

"/var/folders/42/m23kg6y56pqdvsjcyvd7whs00000gn/T/processingaf27fab3d1014b69ae36512a68c9ac1e/237a338c18cf483c8f2265745f5addb4/io.confmatout.file"

-io.out

"/Users/albor/Desktop/remote 
sensing/LT05_L1TP_044034_19900604_20161002_01_T1/model_libsvm_1990.svm"


2017 May 24 15:52:02 : Application.logger (DEBUG) Entering DoExecute 

2017 May 24 15:52:02 : Application.logger (INFO) Elevation management: 
setting default height above ellipsoid to 0 meters 

2017 May 24 15:52:02 : Application.logger (FATAL) No training samples, 
cannot perform SVM training. 

2017 May 24 15:52:02 : Application.logger (FATAL) The following error 
occurred during application execution : 
/Users/Shared/src/orfeo/OTB-5.2.1/Modules/Applications/AppClassification/app/otbTrainImagesClassifier.cxx:360:
 


itk::ERROR: Fatal error caught. Aborting... 

Converting outputs

Loading resulting layers

Algorithm TrainImagesClassifier (libsvm) finished


if you ask this...

Yes, I set -sample.vfn parameter


Anna 

On Wednesday, May 24, 2017 at 2:55:17 PM UTC+1, Poughon Victor wrote:
>
> Hi Anna, can you show us the command you are running ? Or the parameters 
> if you are using the graphical launcher.
>
> Did you remember to set the -sample.vfn parameter (Field name in gui) ? 
> It's the name of the field carrying the class name in the input vectors.
>
> Victor Poughon
> ------------------------------
> *De :* [email protected] <javascript:> [[email protected] 
> <javascript:>] de la part de Anna Alborova [[email protected] 
> <javascript:>]
> *Envoyé :* mercredi 24 mai 2017 15:42
> *À :* otb-users
> *Objet :* [otb-users] problem with training samples while doing libsvm
>
> I keep facing the problem while doing Training Images classification. I 
> click on libsvm, run the process and it shows the error :  No training 
> samples, cannot perform SVM training. 
>
> I can not understand what is the problem. I ve made again and again 
> training samples with a new shape file, however it shows the same problem.
>
> Help me, please.
>
>
> Anna Alborova
>
> -- 
> -- 
> Check the OTB FAQ at
> http://www.orfeo-toolbox.org/FAQ.html
>  
> You received this message because you are subscribed to the Google
> Groups "otb-users" group.
> To post to this group, send email to [email protected] 
> <javascript:>
> To unsubscribe from this group, send email to
> [email protected] <javascript:>
> For more options, visit this group at
> http://groups.google.com/group/otb-users?hl=en
> --- 
> You received this message because you are subscribed to the Google Groups 
> "otb-users" group.
> To unsubscribe from this group and stop receiving emails from it, send an 
> email to [email protected] <javascript:>.
> For more options, visit https://groups.google.com/d/optout.
>

-- 
-- 
Check the OTB FAQ at
http://www.orfeo-toolbox.org/FAQ.html

You received this message because you are subscribed to the Google
Groups "otb-users" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/otb-users?hl=en
--- 
You received this message because you are subscribed to the Google Groups 
"otb-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to