.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.46.4.
.TH OTBCLI_BANDMATH "1" "December 2015" "otbgui_TrainVectorClassifier 5.6.0" "User Commands"
.SH NAME
otbgui_TrainVectorClassifier \- OTB TrainVectorClassifier application
.SH DESCRIPTION
This is the TrainVectorClassifier application, version 5.6.0
Train a classifier based on labeled geometries and a list of features to consider.
.PP
Complete documentation: http://www.orfeo\-toolbox.org/Applications/TrainVectorClassifier.html
.SS "Parameters:"
.TP
\fB\-progress\fR <boolean>
Report progress
.PP
 \fB\-io.stats\fR              <string>         Input XML image statistics file  (optional, off by default)
 \fB\-io.confmatout\fR         <string>         Output confusion matrix  (optional, off by default)
 \fB\-io.out\fR                <string>         Output model  (mandatory)
 \fB\-feat\fR                  <string list>    Field names for training features.  (mandatory, default value is )
 \fB\-cfield\fR                <string>         Field containing the class id for supervision  (mandatory, default value is class)
 \fB\-layer\fR                 <int32>          Layer Index  (optional, on by default, default value is 0)
 \fB\-valid.vd\fR              <string>         Validation Vector Data  (optional, off by default)
 \fB\-valid.layer\fR           <int32>          Layer Index  (optional, on by default, default value is 0)
 \fB\-classifier\fR            <string>         Classifier to use for the training [boost/dt/gbt/ann/bayes/rf/knn] (mandatory, default value is boost)
 \fB\-classifier.boost.t\fR    <string>         Boost Type [discrete/real/logit/gentle] (mandatory, default value is real)
 \fB\-classifier.boost.w\fR    <int32>          Weak count  (mandatory, default value is 100)
 \fB\-classifier.boost.r\fR    <float>          Weight Trim Rate  (mandatory, default value is 0.95)
 \fB\-classifier.boost.m\fR    <int32>          Maximum depth of the tree  (mandatory, default value is 1)
 \fB\-classifier.dt.max\fR     <int32>          Maximum depth of the tree  (mandatory, default value is 65535)
 \fB\-classifier.dt.min\fR     <int32>          Minimum number of samples in each node  (mandatory, default value is 10)
 \fB\-classifier.dt.ra\fR      <float>          Termination criteria for regression tree  (mandatory, default value is 0.01)
 \fB\-classifier.dt.cat\fR     <int32>          Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split  (mandatory, default value is 10)
 \fB\-classifier.dt.f\fR       <int32>          K\fB\-fold\fR cross\fB\-validations\fR  (mandatory, default value is 10)
 \fB\-classifier.dt.r\fR       <boolean>        Set Use1seRule flag to false  (optional, off by default)
 \fB\-classifier.dt.t\fR       <boolean>        Set TruncatePrunedTree flag to false  (optional, off by default)
 \fB\-classifier.gbt.w\fR      <int32>          Number of boosting algorithm iterations  (mandatory, default value is 200)
 \fB\-classifier.gbt.s\fR      <float>          Regularization parameter  (mandatory, default value is 0.01)
 \fB\-classifier.gbt.p\fR      <float>          Portion of the whole training set used for each algorithm iteration  (mandatory, default value is 0.8)
 \fB\-classifier.gbt.max\fR    <int32>          Maximum depth of the tree  (mandatory, default value is 3)
 \fB\-classifier.ann.t\fR      <string>         Train Method Type [reg/back] (mandatory, default value is reg)
 \fB\-classifier.ann.sizes\fR  <string list>    Number of neurons in each intermediate layer  (mandatory)
 \fB\-classifier.ann.f\fR      <string>         Neuron activation function type [ident/sig/gau] (mandatory, default value is sig)
 \fB\-classifier.ann.a\fR      <float>          Alpha parameter of the activation function  (mandatory, default value is 1)
 \fB\-classifier.ann.b\fR      <float>          Beta parameter of the activation function  (mandatory, default value is 1)
 \fB\-classifier.ann.bpdw\fR   <float>          Strength of the weight gradient term in the BACKPROP method  (mandatory, default value is 0.1)
 \fB\-classifier.ann.bpms\fR   <float>          Strength of the momentum term (the difference between weights on the 2 previous iterations)  (mandatory, default value is 0.1)
 \fB\-classifier.ann.rdw\fR    <float>          Initial value Delta_0 of update\fB\-values\fR Delta_{ij} in RPROP method  (mandatory, default value is 0.1)
 \fB\-classifier.ann.rdwm\fR   <float>          Update\fB\-values\fR lower limit Delta_{min} in RPROP method  (mandatory, default value is 1e\fB\-\fR07)
 \fB\-classifier.ann.term\fR   <string>         Termination criteria [iter/eps/all] (mandatory, default value is all)
 \fB\-classifier.ann.eps\fR    <float>          Epsilon value used in the Termination criteria  (mandatory, default value is 0.01)
 \fB\-classifier.ann.iter\fR   <int32>          Maximum number of iterations used in the Termination criteria  (mandatory, default value is 1000)
 \fB\-classifier.rf.max\fR     <int32>          Maximum depth of the tree  (mandatory, default value is 5)
 \fB\-classifier.rf.min\fR     <int32>          Minimum number of samples in each node  (mandatory, default value is 10)
 \fB\-classifier.rf.ra\fR      <float>          Termination Criteria for regression tree  (mandatory, default value is 0)
 \fB\-classifier.rf.cat\fR     <int32>          Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split  (mandatory, default value is 10)
 \fB\-classifier.rf.var\fR     <int32>          Size of the randomly selected subset of features at each tree node  (mandatory, default value is 0)
 \fB\-classifier.rf.nbtrees\fR <int32>          Maximum number of trees in the forest  (mandatory, default value is 100)
 \fB\-classifier.rf.acc\fR     <float>          Sufficient accuracy (OOB error)  (mandatory, default value is 0.01)
 \fB\-classifier.knn.k\fR      <int32>          Number of Neighbors  (mandatory, default value is 32)
 \fB\-rand\fR                  <int32>          set user defined seed  (optional, off by default)
 \fB\-inxml\fR                 <string>         Load otb application from xml file  (optional, off by default)
.SH EXAMPLES
otbgui_TrainVectorClassifier \-io.vd vectorData.shp \-io.stats meanVar.xml \-io.out svmModel.svm \-feat perimeter  area  width \-cfield predicted