.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.46.4.
.TH OTBGUI_TRAINREGRESSION "1" "December 2015" "otbgui_TrainRegression 5.2.0" "User Commands"
.SH NAME
otbgui_TrainRegression \- OTB TrainRegression application
.SH DESCRIPTION
This is the TrainRegression application, version 5.2.0
Train a classifier from multiple images to perform regression.
.PP
Complete documentation: http://www.orfeo\-toolbox.org/Applications/TrainRegression.html
.SS "Parameters:"
.TP
\fB\-progress\fR
<boolean>        Report progress
.PP
 \fB\-io\fR.il                 <string list>    Input Image List  (mandatory)
.TP
\fB\-io\fR.csv
<string>         Input CSV file  (optional, off by default)
.TP
\fB\-io\fR.imstat
<string>         Input XML image statistics file  (optional, off by default)
.PP
 \fB\-io\fR.out                <string>         Output regression model  (mandatory)
.TP
\fB\-sample\fR.mt
<int32>          Maximum training predictors  (mandatory, default value is 1000)
.TP
\fB\-sample\fR.mv
<int32>          Maximum validation predictors  (mandatory, default value is 1000)
.TP
\fB\-sample\fR.vtr
<float>          Training and validation sample ratio  (mandatory, default value is 0.5)
.TP
\fB\-classifier\fR
<string>         Classifier to use for the training [dt/gbt/ann/rf/knn] (mandatory, default value is dt)
.TP
\fB\-classifier\fR.dt.max
<int32>          Maximum depth of the tree  (mandatory, default value is 65535)
.TP
\fB\-classifier\fR.dt.min
<int32>          Minimum number of samples in each node  (mandatory, default value is 10)
.TP
\fB\-classifier\fR.dt.ra
<float>          Termination criteria for regression tree  (mandatory, default value is 0.01)
.TP
\fB\-classifier\fR.dt.cat
<int32>          Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split  (mandatory, default value is 10)
.TP
\fB\-classifier\fR.dt.f
<int32>          K\-fold cross\-validations  (mandatory, default value is 10)
.TP
\fB\-classifier\fR.dt.r
<boolean>        Set Use1seRule flag to false  (optional, off by default)
.TP
\fB\-classifier\fR.dt.t
<boolean>        Set TruncatePrunedTree flag to false  (optional, off by default)
.TP
\fB\-classifier\fR.gbt.t
<string>         Loss Function Type [sqr/abs/hub] (mandatory, default value is sqr)
.TP
\fB\-classifier\fR.gbt.w
<int32>          Number of boosting algorithm iterations  (mandatory, default value is 200)
.TP
\fB\-classifier\fR.gbt.s
<float>          Regularization parameter  (mandatory, default value is 0.01)
.TP
\fB\-classifier\fR.gbt.p
<float>          Portion of the whole training set used for each algorithm iteration  (mandatory, default value is 0.8)
.TP
\fB\-classifier\fR.gbt.max
<int32>          Maximum depth of the tree  (mandatory, default value is 3)
.TP
\fB\-classifier\fR.ann.t
<string>         Train Method Type [reg/back] (mandatory, default value is reg)
.TP
\fB\-classifier\fR.ann.sizes
<string list>    Number of neurons in each intermediate layer  (mandatory)
.TP
\fB\-classifier\fR.ann.f
<string>         Neuron activation function type [ident/sig/gau] (mandatory, default value is sig)
.TP
\fB\-classifier\fR.ann.a
<float>          Alpha parameter of the activation function  (mandatory, default value is 1)
.TP
\fB\-classifier\fR.ann.b
<float>          Beta parameter of the activation function  (mandatory, default value is 1)
.TP
\fB\-classifier\fR.ann.bpdw
<float>          Strength of the weight gradient term in the BACKPROP method  (mandatory, default value is 0.1)
.TP
\fB\-classifier\fR.ann.bpms
<float>          Strength of the momentum term (the difference between weights on the 2 previous iterations)  (mandatory, default value is 0.1)
.TP
\fB\-classifier\fR.ann.rdw
<float>          Initial value Delta_0 of update\-values Delta_{ij} in RPROP method  (mandatory, default value is 0.1)
.TP
\fB\-classifier\fR.ann.rdwm
<float>          Update\-values lower limit Delta_{min} in RPROP method  (mandatory, default value is 1e\-07)
.TP
\fB\-classifier\fR.ann.term
<string>         Termination criteria [iter/eps/all] (mandatory, default value is all)
.TP
\fB\-classifier\fR.ann.eps
<float>          Epsilon value used in the Termination criteria  (mandatory, default value is 0.01)
.TP
\fB\-classifier\fR.ann.iter
<int32>          Maximum number of iterations used in the Termination criteria  (mandatory, default value is 1000)
.TP
\fB\-classifier\fR.rf.max
<int32>          Maximum depth of the tree  (mandatory, default value is 5)
.TP
\fB\-classifier\fR.rf.min
<int32>          Minimum number of samples in each node  (mandatory, default value is 10)
.TP
\fB\-classifier\fR.rf.ra
<float>          Termination Criteria for regression tree  (mandatory, default value is 0)
.TP
\fB\-classifier\fR.rf.cat
<int32>          Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split  (mandatory, default value is 10)
.TP
\fB\-classifier\fR.rf.var
<int32>          Size of the randomly selected subset of features at each tree node  (mandatory, default value is 0)
.TP
\fB\-classifier\fR.rf.nbtrees <int32>
Maximum number of trees in the forest  (mandatory, default value is 100)
.TP
\fB\-classifier\fR.rf.acc
<float>          Sufficient accuracy (OOB error)  (mandatory, default value is 0.01)
.TP
\fB\-classifier\fR.knn.k
<int32>          Number of Neighbors  (mandatory, default value is 32)
.TP
\fB\-classifier\fR.knn.rule
<string>         Decision rule [mean/median] (mandatory, default value is mean)
.TP
\fB\-rand\fR
<int32>          set user defined seed  (optional, off by default)
.TP
\fB\-inxml\fR
<string>         Load otb application from xml file  (optional, off by default)
.SH EXAMPLES
otbgui_TrainRegression \-io.il training_dataset.tif \-io.out regression_model.txt \-io.imstat training_statistics.xml \-classifier libsvm
.PP

.SH "SEE ALSO"
The full documentation for
.B otbgui_TrainRegression
is maintained as a Texinfo manual.  If the
.B info
and
.B otbgui_TrainRegression
programs are properly installed at your site, the command
.IP
.B info otbgui_TrainRegression
.PP
should give you access to the complete manual.