[train0]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run0.train
classselection_train = "*"
examples_train = seq * 100

[test0]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run0.test
classselection_test = "*"
examples_test = seq * 50

[train1]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run1.train
classselection_train = "*"
examples_train = seq * 100

[test1]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run1.test
classselection_test = "*"
examples_test = seq * 50

[train2]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run2.train
classselection_train = "*"
examples_train = seq * 100

[test2]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run2.test
classselection_test = "*"
examples_test = seq * 50

[train3]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run3.train
classselection_train = "*"
examples_train = seq * 100

[test3]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run3.test
classselection_test = "*"
examples_test = seq * 50

[train4]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run4.train
classselection_train = "*"
examples_train = seq * 100

[test4]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run4.test
classselection_test = "*"
examples_test = seq * 50

[train5]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run5.train
classselection_train = "*"
examples_train = seq * 100

[test5]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run5.test
classselection_test = "*"
examples_test = seq * 50

[train6]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run6.train
classselection_train = "*"
examples_train = seq * 100

[test6]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run6.test
classselection_test = "*"
examples_test = seq * 50

[train7]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run7.train
classselection_train = "*"
examples_train = seq * 100

[test7]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run7.test
classselection_test = "*"
examples_test = seq * 50

[train8]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run8.train
classselection_train = "*"
examples_train = seq * 100

[test8]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run8.test
classselection_test = "*"
examples_test = seq * 50

[train9]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run9.train
classselection_train = "*"
examples_train = seq * 100

[test9]
dataset = /home/luetz/data/images/15Scenes/imagesScaled/run9.test
classselection_test = "*"
examples_test = seq * 50


[cache]
#root = "/home/rodner/3rdparty/imagenetBOF/niceFeatures/"
root = "/home/luetz/data/feature-storage/15Scenes/niceFeatures/"

[GP_IL]
trainExPerClass = 1
num_runs = 10
do_classification = true
incrementalAddSize = 3
nrOfIncrements = 30

[main]
# extension of all files in the cache
ext = ".feat"
queryStrategy = gpPredVar

[GPHIKClassifier]
noise =  0.0000001
# no uncertainty for standard classification
uncertaintyPredictionForClassification = false
#--define the uncertainty prediction scheme--
# standatd predictive variance
#uncertaintyPrediction = pred_variance
# use the heuristic as proposed by Kapoor et al.
#uncertaintyPrediction = heuristic
# no classification uncertainty at all?
#uncertaintyPrediction = none

#--define the computation scheme for the predictive variance, if needed--
#if we do not need any predictive variance for this experiment
#varianceApproximation = none
# predictive variance approximation useful for sparse features - really fast
#varianceApproximation = approximate_rough 
# predictive variance approximation with eigenvectors (finer)
varianceApproximation = approximate_fine
nrOfEigenvaluesToConsiderForVarApprox = 2
#exact computation of predictive variance
#varianceApproximation = exact

#--define the optimization method--
optimization_method = none
#optimization_method = downhillsimplex
parameter_lower_bound = 1.0
parameter_upper_bound = 1.0 

#--stuff for the IterativeLinearSolver--
#ils_verbose = true