Execution Time49.36s

Test: rootbench-ConvNetCpuBenchmarks (Passed)
Build: master-x86_64-centos7-clang100-opt-no-rt-cxxmodules (olsnba08.cern.ch) on 2019-11-14 01:39:53
Repository revision: 32b17abcda23e44b64218a42d0ca69cb30cda7e0

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Run on (48 X 3200 MHz CPU s)
2019-11-14 03:24:55
Warning in <TFile::OpenFromCache>: you want to read through a cache, but you have no valid cache directory set - reading remotely
Info in <TFile::OpenFromCache>: set cache directory using TFile::SetCacheFileDir()
--- Classification  : Using input file: imagesData.root
create data set info dataset_cnn_ecal
DataSetInfo              : [dataset_cnn_ecal] : Added class "Signal"
                         : Add Tree sgn of type Signal with 1000 events
DataSetInfo              : [dataset_cnn_ecal] : Added class "Background"
                         : Add Tree bkg of type Background with 1000 events
number of variables is 1024
prepared DATA LOADER 
Factory                  : Booking method: [NON-XML-CHAR-0x1B][1mCNN_CPU[NON-XML-CHAR-0x1B][0m
                         : 
                         : Parsing option string: 
                         : ... "!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=None:WeightInitialization=XAVIERUNIFORM:InputLayout=1|32|32:BatchLayout=32|1|1024:Layout=CONV|12|3|3|1|1|1|1|RELU,CONV|12|3|3|1|1|1|1|RELU,MAXPOOL|2|2|2|2,CONV|12|3|3|1|1|1|1|RELU,CONV|12|3|3|1|1|1|1|RELU,MAXPOOL|2|2|2|2,RESHAPE|1|1|768|FLAT,DENSE|64|RELU,DENSE|32|RELU,DENSE|1|LINEAR:TrainingStrategy=LearningRate=1e-5,Momentum=0.0,Repetitions=1,ConvergenceSteps=10,BatchSize=32,TestRepetitions=1,MaxEpochs=10,Optimizer=ADAM,WeightDecay=1e-4,Regularization=None: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:VarTransform=None:WeightInitialization=XAVIERUNIFORM:InputLayout=1|32|32:BatchLayout=32|1|1024:Layout=CONV|12|3|3|1|1|1|1|RELU,CONV|12|3|3|1|1|1|1|RELU,MAXPOOL|2|2|2|2,CONV|12|3|3|1|1|1|1|RELU,CONV|12|3|3|1|1|1|1|RELU,MAXPOOL|2|2|2|2,RESHAPE|1|1|768|FLAT,DENSE|64|RELU,DENSE|32|RELU,DENSE|1|LINEAR:TrainingStrategy=LearningRate=1e-5,Momentum=0.0,Repetitions=1,ConvergenceSteps=10,BatchSize=32,TestRepetitions=1,MaxEpochs=10,Optimizer=ADAM,WeightDecay=1e-4,Regularization=None:Architecture=CPU"
                         : The following options are set:
                         : - By User:
                         :     V: "True" [Verbose output (short form of "VerbosityLevel" below - overrides the latter one)]
                         :     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)"]
                         :     H: "False" [Print method-specific help message]
                         :     InputLayout: "1|32|32" [The Layout of the input]
                         :     BatchLayout: "32|1|1024" [The Layout of the batch]
                         :     Layout: "CONV|12|3|3|1|1|1|1|RELU,CONV|12|3|3|1|1|1|1|RELU,MAXPOOL|2|2|2|2,CONV|12|3|3|1|1|1|1|RELU,CONV|12|3|3|1|1|1|1|RELU,MAXPOOL|2|2|2|2,RESHAPE|1|1|768|FLAT,DENSE|64|RELU,DENSE|32|RELU,DENSE|1|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-5,Momentum=0.0,Repetitions=1,ConvergenceSteps=10,BatchSize=32,TestRepetitions=1,MaxEpochs=10,Optimizer=ADAM,WeightDecay=1e-4,Regularization=None" [Defines the training strategies.]
                         : - Default:
                         :     VerbosityLevel: "Default" [Verbosity level]
                         :     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
Factory                  : Train method: CNN_CPU for Classification
                         : 
                         : Start of deep neural network training on CPU using (for ROOT-IMT) nthreads = 48
                         : 
                         : *****   Deep Learning Network *****
DEEP NEURAL NETWORK:   Depth = 10  Input = ( 1, 32, 32 )  Batch size = 32  Loss function = C
	Layer 0	 CONV LAYER: 	( W = 32 ,  H = 32 ,  D = 12 ) 	 Filter ( W = 3 ,  H = 3 ) 	Output = ( 32 , 12 , 1024 ) 	 Activation Function = Relu
	Layer 1	 CONV LAYER: 	( W = 32 ,  H = 32 ,  D = 12 ) 	 Filter ( W = 3 ,  H = 3 ) 	Output = ( 32 , 12 , 1024 ) 	 Activation Function = Relu
	Layer 2	 POOL Layer: 	( W = 16 ,  H = 16 ,  D = 12 ) 	 Filter ( W = 2 ,  H = 2 ) 	Output = ( 32 , 12 , 256 ) 
	Layer 3	 CONV LAYER: 	( W = 16 ,  H = 16 ,  D = 12 ) 	 Filter ( W = 3 ,  H = 3 ) 	Output = ( 32 , 12 , 256 ) 	 Activation Function = Relu
	Layer 4	 CONV LAYER: 	( W = 16 ,  H = 16 ,  D = 12 ) 	 Filter ( W = 3 ,  H = 3 ) 	Output = ( 32 , 12 , 256 ) 	 Activation Function = Relu
	Layer 5	 POOL Layer: 	( W = 8 ,  H = 8 ,  D = 12 ) 	 Filter ( W = 2 ,  H = 2 ) 	Output = ( 32 , 12 , 64 ) 
	Layer 6	 RESHAPE Layer 	 Input = ( 12 , 8 , 8 ) 	Output = ( 1 , 32 , 768 ) 
	Layer 7	 DENSE Layer: 	 ( Input =   768 , Width =    64 ) 	Output = (  1 ,    32 ,    64 ) 	 Activation Function = Relu
	Layer 8	 DENSE Layer: 	 ( Input =    64 , Width =    32 ) 	Output = (  1 ,    32 ,    32 ) 	 Activation Function = Relu
	Layer 9	 DENSE Layer: 	 ( Input =    32 , Width =     1 ) 	Output = (  1 ,    32 ,     1 ) 	 Activation Function = Identity
                         : Using 800 events for training and 200 for testing
                         : Training phase 1 of 1:  Optimizer ADAM Learning rate = 1e-05 regularization 0 minimum error = 1.35095
                         : --------------------------------------------------------------
                         :      Epoch |   Train Err.   Val. Err.  t(s)/epoch   t(s)/Loss   nEvents/s Conv. Steps
                         : --------------------------------------------------------------
                         :          1 Minimum Test error found - save the configuration 
                         :          1 |      1.06597    0.995431     3.44526     1.05239     334.327           0
                         :          2 Minimum Test error found - save the configuration 
                         :          2 |     0.964114    0.912611     3.45339     1.05596      333.69           0
                         :          3 Minimum Test error found - save the configuration 
                         :          3 |     0.926372    0.891438     3.44704     1.04912     333.623           0
                         :          4 Minimum Test error found - save the configuration 
                         :          4 |     0.905618    0.870105     3.43058     1.04365     335.157           0
                         :          5 Minimum Test error found - save the configuration 
                         :          5 |     0.889365    0.858784     3.44272      1.0433     333.414           0
                         :          6 Minimum Test error found - save the configuration 
                         :          6 |     0.878839    0.846594     3.44424     1.04847     333.922           0
                         :          7 |     0.869947     0.84789     3.43655     1.04536     334.561           1
                         :          8 Minimum Test error found - save the configuration 
                         :          8 |     0.862191    0.837328     3.43833      1.0457      334.36           0
                         :          9 Minimum Test error found - save the configuration 
                         :          9 |     0.855974    0.834135     3.43169     1.04553     335.267           0
                         :         10 Minimum Test error found - save the configuration 
                         :         10 |     0.849839    0.832009     3.43562     1.04609     334.795           0
                         : 
                         : Elapsed time for training with 1000 events: 34.6 sec         
                         : Evaluate deep neural network on CPU using batches with size = 32
                         : 
CNN_CPU                  : [dataset_cnn_ecal] : Evaluation of CNN_CPU on training sample (1000 events)
                         : Elapsed time for evaluation of 1000 events: 1.16 sec       
Factory                  : Training finished
                         : 
                         : Ranking input variables (method specific)...
                         : No variable ranking supplied by classifier: CNN_CPU
Factory                  : [NON-XML-CHAR-0x1B][1mTest all methods[NON-XML-CHAR-0x1B][0m
Factory                  : Test method: CNN_CPU for Classification performance
                         : 
                         : Evaluate deep neural network on CPU using batches with size = 32
                         : 
CNN_CPU                  : [dataset_cnn_ecal] : Evaluation of CNN_CPU on testing sample (1000 events)
                         : Elapsed time for evaluation of 1000 events: 1.15 sec       
-------------------------------------------------------------------
Benchmark                            Time           CPU Iterations
-------------------------------------------------------------------
BM_ConvolutionalNetwork_CPU 49232146035 ns 48232293103 ns          1