Execution Time4.93s

Test: TMVA-DNN-CNN-MethodDL-CPU (Passed)
Build: master-x86_64-fedora29-gcc8 (root-fedora29-3.cern.ch) on 2019-11-14 04:22:33

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Testing Method DL for CPU backend: 
******************************************************************************
*Tree    :sgn       : sgn                                                    *
*Entries :     2000 : Total =          514306 bytes  File  Size =     463510 *
*        :          : Tree compression factor =   1.10                       *
******************************************************************************
*Br    0 :ximage    : ximage[64]/F                                           *
*Entries :     2000 : Total  Size=     514013 bytes  File Size  =     463510 *
*Baskets :       16 : Basket Size=      32000 bytes  Compression=   1.10     *
*............................................................................*
******************************************************************************
*Tree    :bkg       : bkg                                                    *
*Entries :     2000 : Total =          514306 bytes  File  Size =     458281 *
*        :          : Tree compression factor =   1.11                       *
******************************************************************************
*Br    0 :ximage    : ximage[64]/F                                           *
*Entries :     2000 : Total  Size=     514013 bytes  File Size  =     458281 *
*Baskets :       16 : Basket Size=      32000 bytes  Compression=   1.11     *
*............................................................................*
create data set info dataset
DataSetInfo              : [dataset] : Added class "Signal"
                         : Add Tree sgn of type Signal with 2000 events
DataSetInfo              : [dataset] : Added class "Background"
                         : Add Tree bkg of type Background with 2000 events
Factory                  : You are running ROOT Version: 6.19/01, May 29, 2019
                         : 
                         : _/_/_/_/_/ _|      _|  _|      _|    _|_|   
                         :    _/      _|_|  _|_|  _|      _|  _|    _| 
                         :   _/       _|  _|  _|  _|      _|  _|_|_|_| 
                         :  _/        _|      _|    _|  _|    _|    _| 
                         : _/         _|      _|      _|      _|    _| 
                         : 
                         : ___________TMVA Version 4.2.1, Feb 5, 2015
                         : 
Factory                  : Booking method: [NON-XML-CHAR-0x1B][1mDL_CNN_CPU[NON-XML-CHAR-0x1B][0m
                         : 
                         : Parsing option string: 
                         : ... "!H:V:ErrorStrategy=CROSSENTROPY:WeightInitialization=XAVIERUNIFORM:InputLayout=1|8|8:BatchLayout=256|1|64:Layout=CONV|6|3|3|1|1|0|0|TANH,MAXPOOL|2|2|2|2,RESHAPE|FLAT,DENSE|10|TANH,DENSE|2|LINEAR:TrainingStrategy=LearningRate=1e-1,Optimizer=SGD,Momentum=0.9,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=10,WeightDecay=1e-4,Regularization=L2,MaxEpochs=40DropConfig=0.0+0.5+0.5+0.5|LearningRate=1e-2,Optimizer=SGD,Momentum=0.9,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=5,WeightDecay=1e-4,Regularization=L2,MaxEpochs=20DropConfig=0.0+0.0+0.0+0.0|LearningRate=1e-3,Optimizer=SGD,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=5,WeightDecay=1e-4,Regularization=L2,MaxEpochs=20DropConfig=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=CROSSENTROPY:WeightInitialization=XAVIERUNIFORM:InputLayout=1|8|8:BatchLayout=256|1|64:Layout=CONV|6|3|3|1|1|0|0|TANH,MAXPOOL|2|2|2|2,RESHAPE|FLAT,DENSE|10|TANH,DENSE|2|LINEAR:TrainingStrategy=LearningRate=1e-1,Optimizer=SGD,Momentum=0.9,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=10,WeightDecay=1e-4,Regularization=L2,MaxEpochs=40DropConfig=0.0+0.5+0.5+0.5|LearningRate=1e-2,Optimizer=SGD,Momentum=0.9,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=5,WeightDecay=1e-4,Regularization=L2,MaxEpochs=20DropConfig=0.0+0.0+0.0+0.0|LearningRate=1e-3,Optimizer=SGD,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=5,WeightDecay=1e-4,Regularization=L2,MaxEpochs=20DropConfig=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|8|8" [The Layout of the input]
                         :     BatchLayout: "256|1|64" [The Layout of the batch]
                         :     Layout: "CONV|6|3|3|1|1|0|0|TANH,MAXPOOL|2|2|2|2,RESHAPE|FLAT,DENSE|10|TANH,DENSE|2|LINEAR" [Layout of the network.]
                         :     ErrorStrategy: "CROSSENTROPY" [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-1,Optimizer=SGD,Momentum=0.9,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=10,WeightDecay=1e-4,Regularization=L2,MaxEpochs=40DropConfig=0.0+0.5+0.5+0.5|LearningRate=1e-2,Optimizer=SGD,Momentum=0.9,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=5,WeightDecay=1e-4,Regularization=L2,MaxEpochs=20DropConfig=0.0+0.0+0.0+0.0|LearningRate=1e-3,Optimizer=SGD,Momentum=0.0,Repetitions=1,ConvergenceSteps=20,BatchSize=256,TestRepetitions=5,WeightDecay=1e-4,Regularization=L2,MaxEpochs=20DropConfig=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 Signal
                         : Dataset[dataset] :  create input formulas for tree sgn
                         : Using variable ximage[0] from array expression ximage of size 64
                         : Building event vectors for type 2 Background
                         : Dataset[dataset] :  create input formulas for tree bkg
                         : Using variable ximage[0] from array expression ximage of size 64
DataSetFactory           : [dataset] : Number of events in input trees
                         : 
                         : 
                         : Number of training and testing events
                         : ---------------------------------------------------------------------------
                         : Signal     -- training events            : 1000
                         : Signal     -- testing events             : 1000
                         : Signal     -- training and testing events: 2000
                         : Background -- training events            : 1000
                         : Background -- testing events             : 1000
                         : Background -- training and testing events: 2000
                         : 
Factory                  : Train method: DL_CNN_CPU for Classification
                         : 
                         : Start of deep neural network training on CPU using (for ROOT-IMT) nthreads = 1
                         : 
                         : *****   Deep Learning Network *****
DEEP NEURAL NETWORK:   Depth = 5  Input = ( 1, 8, 8 )  Batch size = 256  Loss function = C
	Layer 0	 CONV LAYER: 	( W = 6 ,  H = 6 ,  D = 6 ) 	 Filter ( W = 3 ,  H = 3 ) 	Output = ( 256 , 6 , 36 ) 	 Activation Function = Tanh
	Layer 1	 POOL Layer: 	( W = 3 ,  H = 3 ,  D = 6 ) 	 Filter ( W = 2 ,  H = 2 ) 	Output = ( 256 , 6 , 9 ) 
	Layer 2	 RESHAPE Layer 	 Input = ( 6 , 3 , 3 ) 	Output = ( 1 , 256 , 54 ) 
	Layer 3	 DENSE Layer: 	 ( Input =    54 , Width =    10 ) 	Output = (  1 ,   256 ,    10 ) 	 Activation Function = Tanh
	Layer 4	 DENSE Layer: 	 ( Input =    10 , Width =     2 ) 	Output = (  1 ,   256 ,     2 ) 	 Activation Function = Identity
                         : Using 1600 events for training and 400 for testing
                         : Training phase 1 of 3:  Optimizer SGD Learning rate = 0.1 regularization 2 minimum error = 0.885106
                         : --------------------------------------------------------------
                         :      Epoch |   Train Err.   Val. Err.  t(s)/epoch   t(s)/Loss   nEvents/s Conv. Steps
                         : --------------------------------------------------------------
                         :         10 Minimum Test error found - save the configuration 
                         :         10 |     0.225322     0.21111   0.0138394  0.00852514      118273           0
                         :         20 |     0.302689    0.287591   0.0133443  0.00827788      122718          10
                         :         30 Minimum Test error found - save the configuration 
                         :         30 |     0.251456    0.184073   0.0140689  0.00833513      116052           0
                         :         40 |     0.258995    0.250546     0.01327  0.00812636      123301          10
                         : 
                         : Using 1600 events for training and 400 for testing
                         : Training phase 2 of 3:  Optimizer SGD Learning rate = 0.01 regularization 2 minimum error = 0.184073
                         : --------------------------------------------------------------
                         :      Epoch |   Train Err.   Val. Err.  t(s)/epoch   t(s)/Loss   nEvents/s Conv. Steps
                         : --------------------------------------------------------------
                         :          5 Minimum Test error found - save the configuration 
                         :          5 |     0.148891    0.124529   0.0141458  0.00833657      123092           0
                         :         10 Minimum Test error found - save the configuration 
                         :         10 |     0.111309    0.108591   0.0142624  0.00838558      122047           0
                         :         15 Minimum Test error found - save the configuration 
                         :         15 |    0.0892508   0.0903313   0.0140881  0.00830805      123607           0
                         :         20 Minimum Test error found - save the configuration 
                         :         20 |    0.0791031    0.086247   0.0160424    0.010878      110768           0
                         : 
                         : Using 1600 events for training and 400 for testing
                         : Training phase 3 of 3:  Optimizer SGD Learning rate = 0.001 regularization 2 minimum error = 0.086247
                         : --------------------------------------------------------------
                         :      Epoch |   Train Err.   Val. Err.  t(s)/epoch   t(s)/Loss   nEvents/s Conv. Steps
                         : --------------------------------------------------------------
                         :          5 Minimum Test error found - save the configuration 
                         :          5 |    0.0757003   0.0761211   0.0156884  0.00841245      109668           0
                         :         10 Minimum Test error found - save the configuration 
                         :         10 |      0.07659    0.076041   0.0140747  0.00826691      123658           0
                         :         15 Minimum Test error found - save the configuration 
                         :         15 |    0.0752133   0.0759709   0.0140701  0.00827938      123729           0
                         :         20 Minimum Test error found - save the configuration 
                         :         20 |    0.0748531   0.0758971   0.0145033  0.00893842      120796           0
                         : 
                         : Elapsed time for training with 2000 events: 1.16 sec         
                         : Evaluate deep neural network on CPU using batches with size = 256
                         : 
DL_CNN_CPU               : [dataset] : Evaluation of DL_CNN_CPU on training sample (2000 events)
                         : Elapsed time for evaluation of 2000 events: 0.0104 sec       
                         : Creating xml weight file: [NON-XML-CHAR-0x1B][0;36mdataset/weights/TMVAClassification_DL_CNN_CPU.weights.xml[NON-XML-CHAR-0x1B][0m
                         : Creating standalone class: [NON-XML-CHAR-0x1B][0;36mdataset/weights/TMVAClassification_DL_CNN_CPU.class.C[NON-XML-CHAR-0x1B][0m
Factory                  : Training finished
                         : 
                         : Ranking input variables (method specific)...
                         : No variable ranking supplied by classifier: DL_CNN_CPU
Factory                  : === Destroy and recreate all methods via weight files for testing ===
                         : 
                         : Reading weight file: [NON-XML-CHAR-0x1B][0;36mdataset/weights/TMVAClassification_DL_CNN_CPU.weights.xml[NON-XML-CHAR-0x1B][0m
Factory                  : [NON-XML-CHAR-0x1B][1mTest all methods[NON-XML-CHAR-0x1B][0m
Factory                  : Test method: DL_CNN_CPU for Classification performance
                         : 
                         : Evaluate deep neural network on CPU using batches with size = 1000
                         : 
DL_CNN_CPU               : [dataset] : Evaluation of DL_CNN_CPU on testing sample (2000 events)
                         : Elapsed time for evaluation of 2000 events: 0.0118 sec       
Factory                  : [NON-XML-CHAR-0x1B][1mEvaluate all methods[NON-XML-CHAR-0x1B][0m
Factory                  : Evaluate classifier: DL_CNN_CPU
                         : 
DL_CNN_CPU               : [dataset] : Loop over test events and fill histograms with classifier response...
                         : 
                         : Evaluate deep neural network on CPU using batches with size = 1000
                         : 
                         : 
                         : Evaluation results ranked by best signal efficiency and purity (area)
                         : -------------------------------------------------------------------------------------------------------------------
                         : DataSet       MVA                       
                         : Name:         Method:          ROC-integ
                         : dataset       DL_CNN_CPU     : 0.996
                         : -------------------------------------------------------------------------------------------------------------------
                         : 
                         : Testing efficiency compared to training efficiency (overtraining check)
                         : -------------------------------------------------------------------------------------------------------------------
                         : DataSet              MVA              Signal efficiency: from test sample (from training sample) 
                         : Name:                Method:          @B=0.01             @B=0.10            @B=0.30   
                         : -------------------------------------------------------------------------------------------------------------------
                         : dataset              DL_CNN_CPU     : 0.966 (0.972)       0.988 (0.990)      0.998 (1.000)
                         : -------------------------------------------------------------------------------------------------------------------
                         : 
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
==> TMVAClassification is done!