TrainVectorClassifier-ann
otbcli_TrainVectorClassifier
TrainVectorClassifier (ann)
Learning
Train a classifier based on labeled geometries and a list of features to consider.
ParameterMultipleInput
io.vd
Input Vector Data
Input geometries used for training (note : all geometries from the layer will be used)
False
ParameterFile
io.stats
Input XML image statistics file
XML file containing mean and variance of each feature.
True
OutputFile
io.confmatout
Output confusion matrix
Output file containing the confusion matrix (.csv format).
OutputFile
io.out
Output model
Output file containing the model estimated (.txt format).
ParameterString
feat
Field names for training features.
List of field names in the input vector data to be used as features for training.
False
ParameterString
cfield
Field containing the class id for supervision
Field containing the class id for supervision. Only geometries with this field available will be taken into account.
class
False
ParameterNumber
layer
Layer Index
Index of the layer to use in the input vector file.
0
True
ParameterMultipleInput
valid.vd
Validation Vector Data
Geometries used for validation (must contain the same fields used for training, all geometries from the layer will be used)
True
ParameterNumber
valid.layer
Layer Index
Index of the layer to use in the validation vector file.
0
True
ParameterSelection
classifier
Classifier to use for the training
Choice of the classifier to use for the training.
ann
0
False
ParameterSelection
classifier.ann.t
Train Method Type
Type of training method for the multilayer perceptron (MLP) neural network.
reg
back
0
False
ParameterString
classifier.ann.sizes
Number of neurons in each intermediate layer
The number of neurons in each intermediate layer (excluding input and output layers).
False
ParameterSelection
classifier.ann.f
Neuron activation function type
Neuron activation function.
ident
sig
gau
1
False
ParameterNumber
classifier.ann.a
Alpha parameter of the activation function
Alpha parameter of the activation function (used only with sigmoid and gaussian functions).
1
False
ParameterNumber
classifier.ann.b
Beta parameter of the activation function
Beta parameter of the activation function (used only with sigmoid and gaussian functions).
1
False
ParameterNumber
classifier.ann.bpdw
Strength of the weight gradient term in the BACKPROP method
Strength of the weight gradient term in the BACKPROP method. The recommended value is about 0.1.
0.1
False
ParameterNumber
classifier.ann.bpms
Strength of the momentum term (the difference between weights on the 2 previous iterations)
Strength of the momentum term (the difference between weights on the 2 previous iterations). This parameter provides some inertia to smooth the random fluctuations of the weights. It can vary from 0 (the feature is disabled) to 1 and beyond. The value 0.1 or so is good enough.
0.1
False
ParameterNumber
classifier.ann.rdw
Initial value Delta_0 of update-values Delta_{ij} in RPROP method
Initial value Delta_0 of update-values Delta_{ij} in RPROP method (default = 0.1).
0.1
False
ParameterNumber
classifier.ann.rdwm
Update-values lower limit Delta_{min} in RPROP method
Update-values lower limit Delta_{min} in RPROP method. It must be positive (default = 1e-7).
1e-07
False
ParameterSelection
classifier.ann.term
Termination criteria
Termination criteria.
iter
eps
all
2
False
ParameterNumber
classifier.ann.eps
Epsilon value used in the Termination criteria
Epsilon value used in the Termination criteria.
0.01
False
ParameterNumber
classifier.ann.iter
Maximum number of iterations used in the Termination criteria
Maximum number of iterations used in the Termination criteria.
1000
False
ParameterNumber
rand
set user defined seed
Set specific seed. with integer value.
0
True