Execution Time5.49s

Test: TMVA-DNN-Regression-Cpu (Passed)
Build: master-x86_64-centos7-gcc62-opt-no-rt-cxxmodules (olsnba08.cern.ch) on 2019-11-14 01:02:24
Repository revision: 32b17abcda23e44b64218a42d0ca69cb30cda7e0

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
create data set info dataset
DataSetInfo              : [dataset] : Added class "Regression"
                         : Add Tree  of type Regression with 50000 events
                         : Dataset[dataset] : Class index : 0  name : Regression
Factory                  : Booking method: [NON-XML-CHAR-0x1B][1mDL_MultiRegCPU[NON-XML-CHAR-0x1B][0m
                         : 
                         : Parsing option string: 
                         : ... "!H:V:ErrorStrategy=SUMOFSQUARES:WeightInitialization=XAVIERUNIFORM:InputLayout=1|1|2:BatchLayout=128|1|2:Layout=RESHAPE|1|1|2|FLAT,DENSE|2|SIGMOID,DENSE|2|LINEAR:TrainingStrategy=LearningRate=1e-3,Momentum=0.0,Repetitions=10,ConvergenceSteps=10,BatchSize=128,TestRepetitions=10,MaxEpochs=100WeightDecay=0,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0:Architecture=CPU"
                         : The following options are set:
                         : - By User:
                         :     <none>
                         : - Default:
                         :     Boost_num: "0" [Number of times the classifier will be boosted]
                         : Parsing option string: 
                         : ... "!H:V:ErrorStrategy=SUMOFSQUARES:WeightInitialization=XAVIERUNIFORM:InputLayout=1|1|2:BatchLayout=128|1|2:Layout=RESHAPE|1|1|2|FLAT,DENSE|2|SIGMOID,DENSE|2|LINEAR:TrainingStrategy=LearningRate=1e-3,Momentum=0.0,Repetitions=10,ConvergenceSteps=10,BatchSize=128,TestRepetitions=10,MaxEpochs=100WeightDecay=0,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0:Architecture=CPU"
                         : The following options are set:
                         : - By User:
                         :     V: "True" [Verbose output (short form of "VerbosityLevel" below - overrides the latter one)]
                         :     H: "False" [Print method-specific help message]
                         :     InputLayout: "1|1|2" [The Layout of the input]
                         :     BatchLayout: "128|1|2" [The Layout of the batch]
                         :     Layout: "RESHAPE|1|1|2|FLAT,DENSE|2|SIGMOID,DENSE|2|LINEAR" [Layout of the network.]
                         :     ErrorStrategy: "SUMOFSQUARES" [Loss function: Mean squared error (regression) or cross entropy (binary classification).]
                         :     WeightInitialization: "XAVIERUNIFORM" [Weight initialization strategy]
                         :     Architecture: "CPU" [Which architecture to perform the training on.]
                         :     TrainingStrategy: "LearningRate=1e-3,Momentum=0.0,Repetitions=10,ConvergenceSteps=10,BatchSize=128,TestRepetitions=10,MaxEpochs=100WeightDecay=0,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0" [Defines the training strategies.]
                         : - Default:
                         :     VerbosityLevel: "Default" [Verbosity level]
                         :     VarTransform: "None" [List of variable transformations performed before training, e.g., "D_Background,P_Signal,G,N_AllClasses" for: "Decorrelation, PCA-transformation, Gaussianisation, Normalisation, each for the given class of events ('AllClasses' denotes all events of all classes, if no class indication is given, 'All' is assumed)"]
                         :     CreateMVAPdfs: "False" [Create PDFs for classifier outputs (signal and background)]
                         :     IgnoreNegWeightsInTraining: "False" [Events with negative weights are ignored in the training (but are included for testing and performance evaluation)]
                         :     RandomSeed: "0" [Random seed used for weight initialization and batch shuffling]
                         :     ValidationSize: "20%" [Part of the training data to use for validation. Specify as 0.2 or 20% to use a fifth of the data set as validation set. Specify as 100 to use exactly 100 events. (Default: 20%)]
                         : Will use now the CPU architecture !
Factory                  : [NON-XML-CHAR-0x1B][1mTrain all methods[NON-XML-CHAR-0x1B][0m
                         : Building event vectors for type 2 Regression
                         : Dataset[dataset] :  create input formulas for tree 
DataSetFactory           : [dataset] : Number of events in input trees
                         : 
                         : Number of training and testing events
                         : ---------------------------------------------------------------------------
                         : Regression -- training events            : 40000
                         : Regression -- testing events             : 10000
                         : Regression -- training and testing events: 50000
                         : 
DataSetInfo              : Correlation matrix (Regression):
                         : ---------------------------
                         :           uniform1 uniform2
                         : uniform1:   +1.000   +0.011
                         : uniform2:   +0.011   +1.000
                         : ---------------------------
DataSetFactory           : [dataset] :  
                         : 
Factory                  : [dataset] : Create Transformation "I" with events from all classes.
                         : 
                         : Transformation, Variable selection : 
                         : Input : variable 'uniform1' <---> Output : variable 'uniform1'
                         : Input : variable 'uniform2' <---> Output : variable 'uniform2'
TFHandler_Factory        :    Variable           Mean           RMS   [        Min           Max ]
                         : --------------------------------------------------------------------------
                         :    uniform1:      0.49917      0.28960   [   1.4620e-05      0.99998 ]
                         :    uniform2:      0.50047      0.28796   [   4.3085e-05       1.0000 ]
                         : uniform_add:      0.99964      0.41055   [    0.0045895       1.9946 ]
                         : uniform_sub:   -0.0012975      0.40624   [     -0.99825      0.99686 ]
                         : --------------------------------------------------------------------------
                         : Ranking input variables (method unspecific)...
Factory                  : Train method: DL_MultiRegCPU for Regression
                         : 
                         : Start of deep neural network training on CPU using (for ROOT-IMT) nthreads = 1
                         : 
                         : *****   Deep Learning Network *****
DEEP NEURAL NETWORK:   Depth = 3  Input = ( 1, 1, 2 )  Batch size = 128  Loss function = R
	Layer 0	 RESHAPE Layer 	 Input = ( 1 , 1 , 2 ) 	Output = ( 1 , 128 , 2 ) 
	Layer 1	 DENSE Layer: 	 ( Input =     2 , Width =     2 ) 	Output = (  1 ,   128 ,     2 ) 	 Activation Function = Sigmoid
	Layer 2	 DENSE Layer: 	 ( Input =     2 , Width =     2 ) 	Output = (  1 ,   128 ,     2 ) 	 Activation Function = Identity
                         : Using 32000 events for training and 8000 for testing
                         : Training phase 1 of 1:  Optimizer ADAM Learning rate = 0.001 regularization 0 minimum error = 2.65034
                         : --------------------------------------------------------------
                         :      Epoch |   Train Err.   Val. Err.  t(s)/epoch   t(s)/Loss   nEvents/s Conv. Steps
                         : --------------------------------------------------------------
                         :         10 Minimum Test error found - save the configuration 
                         :         10 |     0.359951    0.363791   0.0331018   0.0319159 1.06987e+06           0
                         :         20 Minimum Test error found - save the configuration 
                         :         20 |     0.169304    0.170798   0.0334341   0.0306104 1.05356e+06           0
                         :         30 Minimum Test error found - save the configuration 
                         :         30 |     0.122324    0.122449   0.0330463   0.0298638 1.06454e+06           0
                         :         40 Minimum Test error found - save the configuration 
                         :         40 |    0.0853147   0.0850266    0.031797   0.0263577 1.09735e+06           0
                         :         50 Minimum Test error found - save the configuration 
                         :         50 |    0.0452318   0.0450133   0.0307525   0.0265028  1.1387e+06           0
                         :         60 Minimum Test error found - save the configuration 
                         :         60 |    0.0113438   0.0113554    0.030874   0.0262042  1.1326e+06           0
                         :         70 Minimum Test error found - save the configuration 
                         :         70 |   0.00173509  0.00176539    0.030702   0.0263552 1.14015e+06           0
                         :         80 Minimum Test error found - save the configuration 
                         :         80 |   0.00052003 0.000535135   0.0341509   0.0263508 1.01536e+06           0
                         :         90 Minimum Test error found - save the configuration 
                         :         90 |  0.000323128  0.00033032   0.0311755   0.0263838 1.12135e+06           0
                         :        100 Minimum Test error found - save the configuration 
                         :        100 |   0.00027503 0.000280128   0.0309225   0.0288378 1.14128e+06           0
                         : 
                         : Elapsed time for training with 40000 events: 3.22 sec         
                         : Dataset[dataset] : Create results for training
                         : Dataset[dataset] : Evaluation of DL_MultiRegCPU on training sample
                         : Dataset[dataset] : Elapsed time for evaluation of 40000 events: 0.136 sec       
                         : Create variable histograms
                         : Create regression target histograms
                         : Create regression average deviation
                         : Results created
                         : Creating xml weight file: [NON-XML-CHAR-0x1B][0;36mdataset/weights/TMVARegression_DL_MultiRegCPU.weights.xml[NON-XML-CHAR-0x1B][0m
Factory                  : Training finished
                         : 
Factory                  : === Destroy and recreate all methods via weight files for testing ===
                         : 
                         : Reading weight file: [NON-XML-CHAR-0x1B][0;36mdataset/weights/TMVARegression_DL_MultiRegCPU.weights.xml[NON-XML-CHAR-0x1B][0m
Factory                  : [NON-XML-CHAR-0x1B][1mTest all methods[NON-XML-CHAR-0x1B][0m
Factory                  : Test method: DL_MultiRegCPU for Regression performance
                         : 
                         : Dataset[dataset] : Create results for testing
                         : Dataset[dataset] : Evaluation of DL_MultiRegCPU on testing sample
                         : Dataset[dataset] : Elapsed time for evaluation of 10000 events: 0.0398 sec       
                         : Create variable histograms
                         : Create regression target histograms
                         : Create regression average deviation
                         : Results created
Factory                  : [NON-XML-CHAR-0x1B][1mEvaluate all methods[NON-XML-CHAR-0x1B][0m
                         : Evaluate regression method: DL_MultiRegCPU
                         : TestRegression (testing)
                         : Calculate regression for all events
                         : Elapsed time for evaluation of 10000 events: 0.0305 sec       
                         : TestRegression (training)
                         : Calculate regression for all events
                         : Elapsed time for evaluation of 40000 events: 0.118 sec       
TFHandler_DL_MultiRegCPU :    Variable           Mean           RMS   [        Min           Max ]
                         : --------------------------------------------------------------------------
                         :    uniform1:      0.49959      0.28878   [   1.7200e-05      0.99987 ]
                         :    uniform2:      0.49348      0.28799   [   4.1931e-05      0.99975 ]
                         : uniform_add:      0.99307      0.40864   [     0.018889       1.9816 ]
                         : uniform_sub:    0.0061078      0.40704   [     -0.98505      0.98005 ]
                         : --------------------------------------------------------------------------
                         : 
                         : Evaluation results ranked by smallest RMS on test sample:
                         : ("Bias" quotes the mean deviation of the regression from true target.
                         :  "MutInf" is the "Mutual Information" between regression and target.
                         :  Indicated by "_T" are the corresponding "truncated" quantities ob-
                         :  tained when removing events deviating more than 2sigma from average.)
                         : --------------------------------------------------------------------------------------------------
                         : --------------------------------------------------------------------------------------------------
                         : dataset              DL_MultiRegCPU :-0.000356-0.000573   0.0174   0.0139  |  3.122  3.062
                         : --------------------------------------------------------------------------------------------------
                         : 
                         : Evaluation results ranked by smallest RMS on training sample:
                         : (overtraining check)
                         : --------------------------------------------------------------------------------------------------
                         : DataSet Name:         MVA Method:        <Bias>   <Bias_T>    RMS    RMS_T  |  MutInf MutInf_T
                         : --------------------------------------------------------------------------------------------------
                         : dataset              DL_MultiRegCPU :-0.000237-0.000329   0.0174   0.0140  |  3.115  3.052
                         : --------------------------------------------------------------------------------------------------
                         : 
Dataset:dataset          : Created tree 'TestTree' with 10000 events
                         : 
Dataset:dataset          : Created tree 'TrainTree' with 40000 events
                         : 
Factory                  : [NON-XML-CHAR-0x1B][1mThank you for using TMVA![NON-XML-CHAR-0x1B][0m
                         : [NON-XML-CHAR-0x1B][1mFor citation information, please visit: http://tmva.sf.net/citeTMVA.html[NON-XML-CHAR-0x1B][0m
==> Wrote root file: TMVA_DNN_MultiRegression.root
==> TMVARegression is done!
Info in <TCanvas::MakeDefCanvas>:  created default TCanvas with name c1
Info in <TCanvas::Print>: pdf file DL_MultiRegCPU.pdf has been created
< Deviation target 1> = -0.000356112 +/- 0.000173893
< Deviation target 2> = -0.00145172 +/- 0.000159298