Hi everyone, In the frame of my work, I would like to perform some benchmarking regarding the different classifiers implemented in OTB : Suport Vector Machine (SVM), Random Forest (RF) and Artificial Neural Network (ANN).
There were no problems with the two first ones (SVM & RF) but I'm not used to the ANN classifier and I faced some issues to set up the parameters in order to run the classification. Hereafter, please find the message error I got (both GUI application and shell application) : *Application.logger (FATAL) The following error occurred during OTB-application execution: C:\OSGeo4W64\usr\src\osgeo4w\opencv\opencv-2.4.11\modules\ml\src\ann_mlp.cpp:698: error: (-5) output training data should be a floating-point matrix withthe number of rows equal to the number of training samples and the number of columns equal to the size of last (output) layer in function CvANN_MLP::prepare_to_train* At this stage, I only try to perform an ANN classification (TrainImagesClassifier) on one single image (4 bands) with two classes in the output classification (built-up vs non built-up). I first computed the Statistics of the image (ComputeImagesStatistics) and now I try to use the image, the associated statistics and the training data (vector data) to run the classifier. Any suggestion will be highly appreciated, Many thanks, Alexandre -- -- 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.
