This is an example of using a CNN in TMVA. We do classification using a toy image data set that is generated when running the example macro
Running with nthreads = 16
DataSetInfo : [dataset] : Added class "Signal"
: Add Tree sig_tree of type Signal with 5000 events
DataSetInfo : [dataset] : Added class "Background"
: Add Tree bkg_tree of type Background with 5000 events
Factory : Booking method: ␛[1mBDT␛[0m
:
: Building event vectors for type 2 Signal
: Dataset[dataset] : create input formulas for tree sig_tree
: Using variable vars[0] from array expression vars of size 256
: Building event vectors for type 2 Background
: Dataset[dataset] : create input formulas for tree bkg_tree
: Using variable vars[0] from array expression vars of size 256
DataSetFactory : [dataset] : Number of events in input trees
:
:
: Number of training and testing events
: ---------------------------------------------------------------------------
: Signal -- training events : 4000
: Signal -- testing events : 1000
: Signal -- training and testing events: 5000
: Background -- training events : 4000
: Background -- testing events : 1000
: Background -- training and testing events: 5000
:
Factory : Booking method: ␛[1mTMVA_DNN_CPU␛[0m
:
: Parsing option string:
: ... "!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=None:WeightInitialization=XAVIER:Layout=DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,DENSE|1|LINEAR:TrainingStrategy=LearningRate=1e-3,Momentum=0.9,Repetitions=1,ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,MaxEpochs=20,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=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:VarTransform=None:WeightInitialization=XAVIER:Layout=DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,DENSE|1|LINEAR:TrainingStrategy=LearningRate=1e-3,Momentum=0.9,Repetitions=1,ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,MaxEpochs=20,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=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)]
: 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]
: Layout: "DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,DENSE|1|LINEAR" [Layout of the network.]
: ErrorStrategy: "CROSSENTROPY" [Loss function: Mean squared error (regression) or cross entropy (binary classification).]
: WeightInitialization: "XAVIER" [Weight initialization strategy]
: Architecture: "CPU" [Which architecture to perform the training on.]
: TrainingStrategy: "LearningRate=1e-3,Momentum=0.9,Repetitions=1,ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,MaxEpochs=20,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0." [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)]
: InputLayout: "0|0|0" [The Layout of the input]
: BatchLayout: "0|0|0" [The Layout of the batch]
: 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 now use the CPU architecture with BLAS and IMT support !
Factory : Booking method: ␛[1mTMVA_CNN_CPU␛[0m
:
: Parsing option string:
: ... "!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=None:WeightInitialization=XAVIER:InputLayout=1|16|16:Layout=CONV|10|3|3|1|1|1|1|RELU,BNORM,CONV|10|3|3|1|1|1|1|RELU,MAXPOOL|2|2|1|1,RESHAPE|FLAT,DENSE|100|RELU,DENSE|1|LINEAR:TrainingStrategy=LearningRate=1e-3,Momentum=0.9,Repetitions=1,ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,MaxEpochs=20,WeightDecay=1e-4,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=CROSSENTROPY:VarTransform=None:WeightInitialization=XAVIER:InputLayout=1|16|16:Layout=CONV|10|3|3|1|1|1|1|RELU,BNORM,CONV|10|3|3|1|1|1|1|RELU,MAXPOOL|2|2|1|1,RESHAPE|FLAT,DENSE|100|RELU,DENSE|1|LINEAR:TrainingStrategy=LearningRate=1e-3,Momentum=0.9,Repetitions=1,ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,MaxEpochs=20,WeightDecay=1e-4,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)]
: 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|16|16" [The Layout of the input]
: Layout: "CONV|10|3|3|1|1|1|1|RELU,BNORM,CONV|10|3|3|1|1|1|1|RELU,MAXPOOL|2|2|1|1,RESHAPE|FLAT,DENSE|100|RELU,DENSE|1|LINEAR" [Layout of the network.]
: ErrorStrategy: "CROSSENTROPY" [Loss function: Mean squared error (regression) or cross entropy (binary classification).]
: WeightInitialization: "XAVIER" [Weight initialization strategy]
: Architecture: "CPU" [Which architecture to perform the training on.]
: TrainingStrategy: "LearningRate=1e-3,Momentum=0.9,Repetitions=1,ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,MaxEpochs=20,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0" [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)]
: BatchLayout: "0|0|0" [The Layout of the batch]
: 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 now use the CPU architecture with BLAS and IMT support !
Factory : ␛[1mTrain all methods␛[0m
Factory : Train method: BDT for Classification
:
BDT : #events: (reweighted) sig: 4000 bkg: 4000
: #events: (unweighted) sig: 4000 bkg: 4000
: Training 400 Decision Trees ... patience please
: Elapsed time for training with 8000 events: 6.41 sec
BDT : [dataset] : Evaluation of BDT on training sample (8000 events)
: Elapsed time for evaluation of 8000 events: 0.184 sec
: Creating xml weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_BDT.weights.xml␛[0m
: Creating standalone class: ␛[0;36mdataset/weights/TMVA_CNN_Classification_BDT.class.C␛[0m
: TMVA_CNN_ClassificationOutput.root:/dataset/Method_BDT/BDT
Factory : Training finished
:
Factory : Train method: TMVA_DNN_CPU for Classification
:
: Start of deep neural network training on CPU using MT, nthreads = 16
:
: ***** Deep Learning Network *****
DEEP NEURAL NETWORK: Depth = 8 Input = ( 1, 1, 256 ) Batch size = 100 Loss function = C
Layer 0 DENSE Layer: ( Input = 256 , Width = 100 ) Output = ( 1 , 100 , 100 ) Activation Function = Relu
Layer 1 BATCH NORM Layer: Input/Output = ( 100 , 100 , 1 ) Norm dim = 100 axis = -1
Layer 2 DENSE Layer: ( Input = 100 , Width = 100 ) Output = ( 1 , 100 , 100 ) Activation Function = Relu
Layer 3 BATCH NORM Layer: Input/Output = ( 100 , 100 , 1 ) Norm dim = 100 axis = -1
Layer 4 DENSE Layer: ( Input = 100 , Width = 100 ) Output = ( 1 , 100 , 100 ) Activation Function = Relu
Layer 5 BATCH NORM Layer: Input/Output = ( 100 , 100 , 1 ) Norm dim = 100 axis = -1
Layer 6 DENSE Layer: ( Input = 100 , Width = 100 ) Output = ( 1 , 100 , 100 ) Activation Function = Relu
Layer 7 DENSE Layer: ( Input = 100 , Width = 1 ) Output = ( 1 , 100 , 1 ) Activation Function = Identity
: Using 6400 events for training and 1600 for testing
: Compute initial loss on the validation data
: Training phase 1 of 1: Optimizer ADAM (beta1=0.9,beta2=0.999,eps=1e-07) Learning rate = 0.001 regularization 0 minimum error = inf
: --------------------------------------------------------------
: Epoch | Train Err. Val. Err. t(s)/epoch t(s)/Loss nEvents/s Conv. Steps
: --------------------------------------------------------------
: Start epoch iteration ...
: 1 Minimum Test error found - save the configuration
: 1 | 0.764165 0.804883 0.970004 0.0817397 7205.06 0
: 2 Minimum Test error found - save the configuration
: 2 | 0.587023 0.721052 0.978964 0.0859798 7166.98 0
: 3 Minimum Test error found - save the configuration
: 3 | 0.48048 0.623492 0.978669 0.082079 7138.16 0
: 4 Minimum Test error found - save the configuration
: 4 | 0.413928 0.574944 0.972145 0.081604 7186.64 0
: 5 | 0.369913 0.707697 0.974461 0.0808876 7162.26 1
: 6 Minimum Test error found - save the configuration
: 6 | 0.341224 0.478256 0.969659 0.081876 7208.97 0
: 7 Minimum Test error found - save the configuration
: 7 | 0.307892 0.472754 0.968482 0.0816273 7216.52 0
: 8 | 0.296916 0.488932 0.971024 0.0808223 7189.38 1
: 9 | 0.284388 0.513776 0.973601 0.0817725 7176.27 2
: 10 | 0.255926 0.511897 0.969136 0.080793 7204.42 3
: 11 | 0.256289 0.475008 0.973702 0.0810995 7170.04 4
: 12 | 0.241834 0.56309 0.987734 0.0808275 7056.96 5
: 13 | 0.216787 0.58009 1.02429 0.0808227 6783.49 6
:
: Elapsed time for training with 8000 events: 12.8 sec
: Evaluate deep neural network on CPU using batches with size = 100
:
TMVA_DNN_CPU : [dataset] : Evaluation of TMVA_DNN_CPU on training sample (8000 events)
: Elapsed time for evaluation of 8000 events: 0.402 sec
: Creating xml weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_TMVA_DNN_CPU.weights.xml␛[0m
: Creating standalone class: ␛[0;36mdataset/weights/TMVA_CNN_Classification_TMVA_DNN_CPU.class.C␛[0m
Factory : Training finished
:
Factory : Train method: TMVA_CNN_CPU for Classification
:
: Start of deep neural network training on CPU using MT, nthreads = 16
:
: ***** Deep Learning Network *****
DEEP NEURAL NETWORK: Depth = 7 Input = ( 1, 16, 16 ) Batch size = 100 Loss function = C
Layer 0 CONV LAYER: ( W = 16 , H = 16 , D = 10 ) Filter ( W = 3 , H = 3 ) Output = ( 100 , 10 , 10 , 256 ) Activation Function = Relu
Layer 1 BATCH NORM Layer: Input/Output = ( 10 , 256 , 100 ) Norm dim = 10 axis = 1
Layer 2 CONV LAYER: ( W = 16 , H = 16 , D = 10 ) Filter ( W = 3 , H = 3 ) Output = ( 100 , 10 , 10 , 256 ) Activation Function = Relu
Layer 3 POOL Layer: ( W = 15 , H = 15 , D = 10 ) Filter ( W = 2 , H = 2 ) Output = ( 100 , 10 , 10 , 225 )
Layer 4 RESHAPE Layer Input = ( 10 , 15 , 15 ) Output = ( 1 , 100 , 2250 )
Layer 5 DENSE Layer: ( Input = 2250 , Width = 100 ) Output = ( 1 , 100 , 100 ) Activation Function = Relu
Layer 6 DENSE Layer: ( Input = 100 , Width = 1 ) Output = ( 1 , 100 , 1 ) Activation Function = Identity
: Using 6400 events for training and 1600 for testing
: Compute initial loss on the validation data
: Training phase 1 of 1: Optimizer ADAM (beta1=0.9,beta2=0.999,eps=1e-07) Learning rate = 0.001 regularization 0 minimum error = inf
: --------------------------------------------------------------
: Epoch | Train Err. Val. Err. t(s)/epoch t(s)/Loss nEvents/s Conv. Steps
: --------------------------------------------------------------
: Start epoch iteration ...
: 1 Minimum Test error found - save the configuration
: 1 | 0.880715 0.654781 6.56798 0.50596 1055.75 0
: 2 Minimum Test error found - save the configuration
: 2 | 0.5888 0.542195 6.61658 0.508628 1047.81 0
: 3 Minimum Test error found - save the configuration
: 3 | 0.479711 0.478808 6.62242 0.521013 1048.94 0
: 4 Minimum Test error found - save the configuration
: 4 | 0.449541 0.425081 6.67876 0.518078 1038.85 0
: 5 | 0.402947 0.476722 6.62993 0.516162 1046.82 1
: 6 | 0.399293 0.444414 6.6716 0.524761 1041.19 2
: 7 Minimum Test error found - save the configuration
: 7 | 0.393605 0.419727 6.67033 0.519914 1040.58 0
: 8 Minimum Test error found - save the configuration
: 8 | 0.374307 0.389117 6.67132 0.528896 1041.93 0
: 9 Minimum Test error found - save the configuration
: 9 | 0.345162 0.381626 6.70533 0.518397 1034.44 0
: 10 | 0.375481 0.475314 6.65496 0.514392 1042.25 1
: 11 | 0.339019 0.391698 6.82521 0.51228 1013.79 2
: 12 | 0.330023 0.442089 7.31129 0.511916 941.263 3
: 13 Minimum Test error found - save the configuration
: 13 | 0.313905 0.37102 7.62979 0.522777 900.519 0
: 14 | 0.307148 0.389217 7.53395 0.512511 911.494 1
: 15 | 0.315008 0.394759 7.42111 0.511237 926.211 2
: 16 | 0.326447 0.375951 7.46949 0.525684 921.685 3
: 17 | 0.318361 0.393118 7.44958 0.515049 922.918 4
: 18 | 0.289545 0.388169 7.44576 0.509831 922.731 5
: 19 | 0.291238 0.395734 7.46016 0.517084 921.782 6
:
: Elapsed time for training with 8000 events: 134 sec
: Evaluate deep neural network on CPU using batches with size = 100
:
TMVA_CNN_CPU : [dataset] : Evaluation of TMVA_CNN_CPU on training sample (8000 events)
: Elapsed time for evaluation of 8000 events: 2.57 sec
: Creating xml weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_TMVA_CNN_CPU.weights.xml␛[0m
: Creating standalone class: ␛[0;36mdataset/weights/TMVA_CNN_Classification_TMVA_CNN_CPU.class.C␛[0m
Factory : Training finished
:
: Ranking input variables (method specific)...
BDT : Ranking result (top variable is best ranked)
: --------------------------------------
: Rank : Variable : Variable Importance
: --------------------------------------
: 1 : vars : 1.114e-02
: 2 : vars : 1.068e-02
: 3 : vars : 1.046e-02
: 4 : vars : 1.034e-02
: 5 : vars : 1.026e-02
: 6 : vars : 1.023e-02
: 7 : vars : 9.767e-03
: 8 : vars : 9.465e-03
: 9 : vars : 9.241e-03
: 10 : vars : 9.181e-03
: 11 : vars : 9.058e-03
: 12 : vars : 8.970e-03
: 13 : vars : 8.872e-03
: 14 : vars : 8.871e-03
: 15 : vars : 8.793e-03
: 16 : vars : 8.735e-03
: 17 : vars : 8.637e-03
: 18 : vars : 8.615e-03
: 19 : vars : 8.523e-03
: 20 : vars : 8.469e-03
: 21 : vars : 8.206e-03
: 22 : vars : 8.206e-03
: 23 : vars : 7.991e-03
: 24 : vars : 7.900e-03
: 25 : vars : 7.853e-03
: 26 : vars : 7.816e-03
: 27 : vars : 7.736e-03
: 28 : vars : 7.615e-03
: 29 : vars : 7.600e-03
: 30 : vars : 7.598e-03
: 31 : vars : 7.571e-03
: 32 : vars : 7.565e-03
: 33 : vars : 7.531e-03
: 34 : vars : 7.406e-03
: 35 : vars : 7.358e-03
: 36 : vars : 7.350e-03
: 37 : vars : 7.163e-03
: 38 : vars : 7.146e-03
: 39 : vars : 7.117e-03
: 40 : vars : 7.101e-03
: 41 : vars : 7.068e-03
: 42 : vars : 7.019e-03
: 43 : vars : 6.854e-03
: 44 : vars : 6.812e-03
: 45 : vars : 6.608e-03
: 46 : vars : 6.548e-03
: 47 : vars : 6.541e-03
: 48 : vars : 6.523e-03
: 49 : vars : 6.516e-03
: 50 : vars : 6.502e-03
: 51 : vars : 6.489e-03
: 52 : vars : 6.450e-03
: 53 : vars : 6.162e-03
: 54 : vars : 6.161e-03
: 55 : vars : 6.142e-03
: 56 : vars : 6.138e-03
: 57 : vars : 6.132e-03
: 58 : vars : 6.123e-03
: 59 : vars : 6.115e-03
: 60 : vars : 6.011e-03
: 61 : vars : 5.955e-03
: 62 : vars : 5.906e-03
: 63 : vars : 5.905e-03
: 64 : vars : 5.890e-03
: 65 : vars : 5.851e-03
: 66 : vars : 5.812e-03
: 67 : vars : 5.746e-03
: 68 : vars : 5.714e-03
: 69 : vars : 5.608e-03
: 70 : vars : 5.605e-03
: 71 : vars : 5.587e-03
: 72 : vars : 5.579e-03
: 73 : vars : 5.569e-03
: 74 : vars : 5.540e-03
: 75 : vars : 5.536e-03
: 76 : vars : 5.429e-03
: 77 : vars : 5.353e-03
: 78 : vars : 5.316e-03
: 79 : vars : 5.309e-03
: 80 : vars : 5.223e-03
: 81 : vars : 5.080e-03
: 82 : vars : 5.047e-03
: 83 : vars : 4.961e-03
: 84 : vars : 4.917e-03
: 85 : vars : 4.881e-03
: 86 : vars : 4.874e-03
: 87 : vars : 4.871e-03
: 88 : vars : 4.772e-03
: 89 : vars : 4.728e-03
: 90 : vars : 4.723e-03
: 91 : vars : 4.681e-03
: 92 : vars : 4.663e-03
: 93 : vars : 4.628e-03
: 94 : vars : 4.592e-03
: 95 : vars : 4.558e-03
: 96 : vars : 4.552e-03
: 97 : vars : 4.534e-03
: 98 : vars : 4.528e-03
: 99 : vars : 4.523e-03
: 100 : vars : 4.518e-03
: 101 : vars : 4.483e-03
: 102 : vars : 4.452e-03
: 103 : vars : 4.390e-03
: 104 : vars : 4.385e-03
: 105 : vars : 4.359e-03
: 106 : vars : 4.344e-03
: 107 : vars : 4.333e-03
: 108 : vars : 4.313e-03
: 109 : vars : 4.238e-03
: 110 : vars : 4.220e-03
: 111 : vars : 4.143e-03
: 112 : vars : 4.140e-03
: 113 : vars : 4.072e-03
: 114 : vars : 4.048e-03
: 115 : vars : 4.045e-03
: 116 : vars : 4.024e-03
: 117 : vars : 4.011e-03
: 118 : vars : 4.007e-03
: 119 : vars : 3.967e-03
: 120 : vars : 3.930e-03
: 121 : vars : 3.904e-03
: 122 : vars : 3.890e-03
: 123 : vars : 3.841e-03
: 124 : vars : 3.818e-03
: 125 : vars : 3.804e-03
: 126 : vars : 3.783e-03
: 127 : vars : 3.609e-03
: 128 : vars : 3.567e-03
: 129 : vars : 3.560e-03
: 130 : vars : 3.555e-03
: 131 : vars : 3.530e-03
: 132 : vars : 3.511e-03
: 133 : vars : 3.510e-03
: 134 : vars : 3.507e-03
: 135 : vars : 3.505e-03
: 136 : vars : 3.500e-03
: 137 : vars : 3.469e-03
: 138 : vars : 3.365e-03
: 139 : vars : 3.337e-03
: 140 : vars : 3.336e-03
: 141 : vars : 3.319e-03
: 142 : vars : 3.318e-03
: 143 : vars : 3.316e-03
: 144 : vars : 3.302e-03
: 145 : vars : 3.209e-03
: 146 : vars : 3.182e-03
: 147 : vars : 3.129e-03
: 148 : vars : 3.097e-03
: 149 : vars : 3.071e-03
: 150 : vars : 3.059e-03
: 151 : vars : 3.030e-03
: 152 : vars : 2.988e-03
: 153 : vars : 2.956e-03
: 154 : vars : 2.926e-03
: 155 : vars : 2.872e-03
: 156 : vars : 2.810e-03
: 157 : vars : 2.796e-03
: 158 : vars : 2.781e-03
: 159 : vars : 2.775e-03
: 160 : vars : 2.730e-03
: 161 : vars : 2.728e-03
: 162 : vars : 2.724e-03
: 163 : vars : 2.722e-03
: 164 : vars : 2.689e-03
: 165 : vars : 2.665e-03
: 166 : vars : 2.621e-03
: 167 : vars : 2.565e-03
: 168 : vars : 2.556e-03
: 169 : vars : 2.533e-03
: 170 : vars : 2.508e-03
: 171 : vars : 2.496e-03
: 172 : vars : 2.485e-03
: 173 : vars : 2.471e-03
: 174 : vars : 2.445e-03
: 175 : vars : 2.397e-03
: 176 : vars : 2.373e-03
: 177 : vars : 2.350e-03
: 178 : vars : 2.335e-03
: 179 : vars : 2.282e-03
: 180 : vars : 2.277e-03
: 181 : vars : 2.233e-03
: 182 : vars : 2.231e-03
: 183 : vars : 2.223e-03
: 184 : vars : 2.194e-03
: 185 : vars : 2.181e-03
: 186 : vars : 2.155e-03
: 187 : vars : 2.118e-03
: 188 : vars : 2.090e-03
: 189 : vars : 2.078e-03
: 190 : vars : 2.058e-03
: 191 : vars : 2.033e-03
: 192 : vars : 2.025e-03
: 193 : vars : 2.010e-03
: 194 : vars : 2.006e-03
: 195 : vars : 1.955e-03
: 196 : vars : 1.941e-03
: 197 : vars : 1.838e-03
: 198 : vars : 1.822e-03
: 199 : vars : 1.811e-03
: 200 : vars : 1.797e-03
: 201 : vars : 1.782e-03
: 202 : vars : 1.761e-03
: 203 : vars : 1.669e-03
: 204 : vars : 1.636e-03
: 205 : vars : 1.565e-03
: 206 : vars : 1.486e-03
: 207 : vars : 1.420e-03
: 208 : vars : 1.389e-03
: 209 : vars : 1.355e-03
: 210 : vars : 9.952e-04
: 211 : vars : 8.570e-04
: 212 : vars : 4.714e-04
: 213 : vars : 0.000e+00
: 214 : vars : 0.000e+00
: 215 : vars : 0.000e+00
: 216 : vars : 0.000e+00
: 217 : vars : 0.000e+00
: 218 : vars : 0.000e+00
: 219 : vars : 0.000e+00
: 220 : vars : 0.000e+00
: 221 : vars : 0.000e+00
: 222 : vars : 0.000e+00
: 223 : vars : 0.000e+00
: 224 : vars : 0.000e+00
: 225 : vars : 0.000e+00
: 226 : vars : 0.000e+00
: 227 : vars : 0.000e+00
: 228 : vars : 0.000e+00
: 229 : vars : 0.000e+00
: 230 : vars : 0.000e+00
: 231 : vars : 0.000e+00
: 232 : vars : 0.000e+00
: 233 : vars : 0.000e+00
: 234 : vars : 0.000e+00
: 235 : vars : 0.000e+00
: 236 : vars : 0.000e+00
: 237 : vars : 0.000e+00
: 238 : vars : 0.000e+00
: 239 : vars : 0.000e+00
: 240 : vars : 0.000e+00
: 241 : vars : 0.000e+00
: 242 : vars : 0.000e+00
: 243 : vars : 0.000e+00
: 244 : vars : 0.000e+00
: 245 : vars : 0.000e+00
: 246 : vars : 0.000e+00
: 247 : vars : 0.000e+00
: 248 : vars : 0.000e+00
: 249 : vars : 0.000e+00
: 250 : vars : 0.000e+00
: 251 : vars : 0.000e+00
: 252 : vars : 0.000e+00
: 253 : vars : 0.000e+00
: 254 : vars : 0.000e+00
: 255 : vars : 0.000e+00
: 256 : vars : 0.000e+00
: --------------------------------------
: No variable ranking supplied by classifier: TMVA_DNN_CPU
: No variable ranking supplied by classifier: TMVA_CNN_CPU
TH1.Print Name = TrainingHistory_TMVA_DNN_CPU_trainingError, Entries= 0, Total sum= 4.81677
TH1.Print Name = TrainingHistory_TMVA_DNN_CPU_valError, Entries= 0, Total sum= 7.51587
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_trainingError, Entries= 0, Total sum= 7.52026
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_valError, Entries= 0, Total sum= 8.22954
Factory : === Destroy and recreate all methods via weight files for testing ===
:
: Reading weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_BDT.weights.xml␛[0m
: Reading weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_TMVA_DNN_CPU.weights.xml␛[0m
: Reading weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_TMVA_CNN_CPU.weights.xml␛[0m
Factory : ␛[1mTest all methods␛[0m
Factory : Test method: BDT for Classification performance
:
BDT : [dataset] : Evaluation of BDT on testing sample (2000 events)
: Elapsed time for evaluation of 2000 events: 0.0426 sec
Factory : Test method: TMVA_DNN_CPU for Classification performance
:
: Evaluate deep neural network on CPU using batches with size = 1000
:
TMVA_DNN_CPU : [dataset] : Evaluation of TMVA_DNN_CPU on testing sample (2000 events)
: Elapsed time for evaluation of 2000 events: 0.0885 sec
Factory : Test method: TMVA_CNN_CPU for Classification performance
:
: Evaluate deep neural network on CPU using batches with size = 1000
:
TMVA_CNN_CPU : [dataset] : Evaluation of TMVA_CNN_CPU on testing sample (2000 events)
: Elapsed time for evaluation of 2000 events: 0.64 sec
Factory : ␛[1mEvaluate all methods␛[0m
Factory : Evaluate classifier: BDT
:
BDT : [dataset] : Loop over test events and fill histograms with classifier response...
:
: Dataset[dataset] : variable plots are not produces ! The number of variables is 256 , it is larger than 200
Factory : Evaluate classifier: TMVA_DNN_CPU
:
TMVA_DNN_CPU : [dataset] : Loop over test events and fill histograms with classifier response...
:
: Evaluate deep neural network on CPU using batches with size = 1000
:
: Dataset[dataset] : variable plots are not produces ! The number of variables is 256 , it is larger than 200
Factory : Evaluate classifier: TMVA_CNN_CPU
:
TMVA_CNN_CPU : [dataset] : Loop over test events and fill histograms with classifier response...
:
: Evaluate deep neural network on CPU using batches with size = 1000
:
: Dataset[dataset] : variable plots are not produces ! The number of variables is 256 , it is larger than 200
:
: Evaluation results ranked by best signal efficiency and purity (area)
: -------------------------------------------------------------------------------------------------------------------
: DataSet MVA
: Name: Method: ROC-integ
: dataset TMVA_CNN_CPU : 0.916
: dataset TMVA_DNN_CPU : 0.885
: dataset BDT : 0.839
: -------------------------------------------------------------------------------------------------------------------
:
: 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 TMVA_CNN_CPU : 0.325 (0.460) 0.742 (0.802) 0.933 (0.940)
: dataset TMVA_DNN_CPU : 0.315 (0.390) 0.663 (0.739) 0.873 (0.902)
: dataset BDT : 0.140 (0.305) 0.554 (0.662) 0.814 (0.862)
: -------------------------------------------------------------------------------------------------------------------
:
Dataset:dataset : Created tree 'TestTree' with 2000 events
:
Dataset:dataset : Created tree 'TrainTree' with 8000 events
:
Factory : ␛[1mThank you for using TMVA!␛[0m
: ␛[1mFor citation information, please visit: http://tmva.sf.net/citeTMVA.html␛[0m
void MakeImagesTree(
int n,
int nh,
int nw)
{
const int ntot = nh * nw;
const int nRndmEvts = 10000;
double delta_sigma = 0.1;
double pixelNoise = 5;
double sX1 = 3;
double sY1 = 3;
double sX2 = sX1 + delta_sigma;
double sY2 = sY1 - delta_sigma;
auto h1 =
new TH2D(
"h1",
"h1", nh, 0, 10, nw, 0, 10);
auto h2 =
new TH2D(
"h2",
"h2", nh, 0, 10, nw, 0, 10);
auto f1 =
new TF2(
"f1",
"xygaus");
auto f2 =
new TF2(
"f2",
"xygaus");
TTree sgn(
"sig_tree",
"signal_tree");
TTree bkg(
"bkg_tree",
"bakground_tree");
TFile f(fileOutName,
"RECREATE");
std::vector<float>
x1(ntot);
std::vector<float>
x2(ntot);
std::vector<float> *px1 = &
x1;
std::vector<float> *px2 = &
x2;
bkg.Branch("vars", "std::vector<float>", &px1);
sgn.Branch("vars", "std::vector<float>", &px2);
f2->SetParameters(1, 5, sX2, 5, sY2);
std::cout << "Filling ROOT tree " << std::endl;
for (
int i = 0; i <
n; ++i) {
if (i % 1000 == 0)
std::cout << "Generating image event ... " << i << std::endl;
h2->Reset();
h2->FillRandom("f2", nRndmEvts);
for (int k = 0; k < nh; ++k) {
for (
int l = 0;
l < nw; ++
l) {
}
}
sgn.Fill();
bkg.Fill();
}
sgn.Write();
bkg.Write();
Info(
"MakeImagesTree",
"Signal and background tree with images data written to the file %s",
f.GetName());
sgn.Print();
bkg.Print();
}
void TMVA_CNN_Classification(std::vector<bool> opt = {1, 1, 1, 1, 1})
{
bool useTMVACNN = (opt.size() > 0) ? opt[0] : false;
bool useKerasCNN = (opt.size() > 1) ? opt[1] : false;
bool useTMVADNN = (opt.size() > 2) ? opt[2] : false;
bool useTMVABDT = (opt.size() > 3) ? opt[3] : false;
bool usePyTorchCNN = (opt.size() > 4) ? opt[4] : false;
#ifndef R__HAS_TMVACPU
#ifndef R__HAS_TMVAGPU
"TMVA is not build with GPU or CPU multi-thread support. Cannot use TMVA Deep Learning for CNN");
useTMVACNN = false;
#endif
#endif
bool writeOutputFile = true;
int num_threads = 0;
if (num_threads >= 0) {
}
else
#ifdef R__HAS_PYMVA
#else
useKerasCNN = false;
#endif
TFile *outputFile =
nullptr;
if (writeOutputFile)
outputFile =
TFile::Open(
"TMVA_CNN_ClassificationOutput.root",
"RECREATE");
"TMVA_CNN_Classification", outputFile,
"!V:ROC:!Silent:Color:AnalysisType=Classification:Transformations=None:!Correlations");
int imgSize = 16 * 16;
TString inputFileName =
"images_data_16x16.root";
if (!fileExist) {
MakeImagesTree(5000, 16, 16);
}
if (!inputFile) {
Error(
"TMVA_CNN_Classification",
"Error opening input file %s - exit", inputFileName.
Data());
return;
}
TTree *signalTree = (
TTree *)inputFile->Get(
"sig_tree");
TTree *backgroundTree = (
TTree *)inputFile->Get(
"bkg_tree");
int nTrainSig = 0.8 * nEventsSig;
int nTrainBkg = 0.8 * nEventsBkg;
"nTrain_Signal=%d:nTrain_Background=%d:SplitMode=Random:SplitSeed=100:NormMode=NumEvents:!V:!CalcCorrelations",
nTrainSig, nTrainBkg);
if (useTMVABDT) {
"!V:NTrees=400:MinNodeSize=2.5%:MaxDepth=2:BoostType=AdaBoost:AdaBoostBeta=0.5:"
"UseBaggedBoost:BaggedSampleFraction=0.5:SeparationType=GiniIndex:nCuts=20");
}
if (useTMVADNN) {
"Layout=DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,DENSE|1|LINEAR");
TString trainingString1(
"LearningRate=1e-3,Momentum=0.9,Repetitions=1,"
"ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,"
"MaxEpochs=20,WeightDecay=1e-4,Regularization=None,"
"Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.");
TString trainingStrategyString(
"TrainingStrategy=");
trainingStrategyString += trainingString1;
TString dnnOptions(
"!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=None:"
"WeightInitialization=XAVIER");
dnnOptions.Append(":");
dnnOptions.Append(layoutString);
dnnOptions.Append(":");
dnnOptions.Append(trainingStrategyString);
TString dnnMethodName =
"TMVA_DNN_CPU";
#ifdef R__HAS_TMVAGPU
dnnOptions += ":Architecture=GPU";
dnnMethodName = "TMVA_DNN_GPU";
#elif defined(R__HAS_TMVACPU)
dnnOptions += ":Architecture=CPU";
#endif
}
if (useTMVACNN) {
TString inputLayoutString(
"InputLayout=1|16|16");
TString layoutString(
"Layout=CONV|10|3|3|1|1|1|1|RELU,BNORM,CONV|10|3|3|1|1|1|1|RELU,MAXPOOL|2|2|1|1,"
"RESHAPE|FLAT,DENSE|100|RELU,DENSE|1|LINEAR");
TString trainingString1(
"LearningRate=1e-3,Momentum=0.9,Repetitions=1,"
"ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,"
"MaxEpochs=20,WeightDecay=1e-4,Regularization=None,"
"Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0");
TString trainingStrategyString(
"TrainingStrategy=");
trainingStrategyString +=
trainingString1;
TString cnnOptions(
"!H:V:ErrorStrategy=CROSSENTROPY:VarTransform=None:"
"WeightInitialization=XAVIER");
cnnOptions.Append(":");
cnnOptions.Append(inputLayoutString);
cnnOptions.Append(":");
cnnOptions.Append(layoutString);
cnnOptions.Append(":");
cnnOptions.Append(trainingStrategyString);
TString cnnMethodName =
"TMVA_CNN_CPU";
#ifdef R__HAS_TMVAGPU
cnnOptions += ":Architecture=GPU";
cnnMethodName = "TMVA_CNN_GPU";
#else
cnnOptions += ":Architecture=CPU";
cnnMethodName = "TMVA_CNN_CPU";
#endif
}
if (useKerasCNN) {
Info(
"TMVA_CNN_Classification",
"Building convolutional keras model");
m.AddLine(
"import tensorflow");
m.AddLine(
"from tensorflow.keras.models import Sequential");
m.AddLine(
"from tensorflow.keras.optimizers import Adam");
"from tensorflow.keras.layers import Input, Dense, Dropout, Flatten, Conv2D, MaxPooling2D, Reshape, BatchNormalization");
m.AddLine(
"model = Sequential() ");
m.AddLine(
"model.add(Reshape((16, 16, 1), input_shape = (256, )))");
m.AddLine(
"model.add(Conv2D(10, kernel_size = (3, 3), kernel_initializer = 'glorot_normal',activation = "
"'relu', padding = 'same'))");
m.AddLine(
"model.add(BatchNormalization())");
m.AddLine(
"model.add(Conv2D(10, kernel_size = (3, 3), kernel_initializer = 'glorot_normal',activation = "
"'relu', padding = 'same'))");
m.AddLine(
"model.add(MaxPooling2D(pool_size = (2, 2), strides = (1,1))) ");
m.AddLine(
"model.add(Flatten())");
m.AddLine(
"model.add(Dense(256, activation = 'relu')) ");
m.AddLine(
"model.add(Dense(2, activation = 'sigmoid')) ");
m.AddLine(
"model.compile(loss = 'binary_crossentropy', optimizer = Adam(lr = 0.001), metrics = ['accuracy'])");
m.AddLine(
"model.save('model_cnn.h5')");
m.AddLine(
"model.summary()");
m.SaveSource(
"make_cnn_model.py");
Warning(
"TMVA_CNN_Classification",
"Error creating Keras model file - skip using Keras");
} else {
Info(
"TMVA_CNN_Classification",
"Booking tf.Keras CNN model");
factory.BookMethod(
"H:!V:VarTransform=None:FilenameModel=model_cnn.h5:tf.keras:"
"FilenameTrainedModel=trained_model_cnn.h5:NumEpochs=20:BatchSize=100:"
"GpuOptions=allow_growth=True");
}
}
if (usePyTorchCNN) {
Info(
"TMVA_CNN_Classification",
"Using Convolutional PyTorch Model");
TString pyTorchFileName =
gROOT->GetTutorialDir() +
TString(
"/tmva/PyTorch_Generate_CNN_Model.py");
Warning(
"TMVA_CNN_Classification",
"PyTorch is not installed or model building file is not existing - skip using PyTorch");
}
else {
Info(
"TMVA_CNN_Classification",
"Booking PyTorch CNN model");
TString methodOpt =
"H:!V:VarTransform=None:FilenameModel=PyTorchModelCNN.pt:"
"FilenameTrainedModel=PyTorchTrainedModelCNN.pt:NumEpochs=20:BatchSize=100";
methodOpt +=
TString(
":UserCode=") + pyTorchFileName;
}
}
factory.TrainAllMethods();
factory.TestAllMethods();
factory.EvaluateAllMethods();
auto c1 = factory.GetROCCurve(loader);
}
static const double x2[5]
static const double x1[5]
void Info(const char *location, const char *msgfmt,...)
Use this function for informational messages.
void Error(const char *location, const char *msgfmt,...)
Use this function in case an error occurred.
void Warning(const char *location, const char *msgfmt,...)
Use this function in warning situations.
R__EXTERN TRandom * gRandom
R__EXTERN TSystem * gSystem
A specialized string object used for TTree selections.
virtual void SetParameters(const Double_t *params)
virtual void SetParameter(Int_t param, Double_t value)
A 2-Dim function with parameters.
A ROOT file is a suite of consecutive data records (TKey instances) with a well defined format.
static TFile * Open(const char *name, Option_t *option="", const char *ftitle="", Int_t compress=ROOT::RCompressionSetting::EDefaults::kUseCompiledDefault, Int_t netopt=0)
Create / open a file.
void Close(Option_t *option="") override
Close a file.
virtual void Reset(Option_t *option="")
Reset.
virtual void FillRandom(const char *fname, Int_t ntimes=5000, TRandom *rng=nullptr)
Fill histogram following distribution in function fname.
virtual Double_t GetBinContent(Int_t bin) const
Return content of bin number bin.
2-D histogram with a double per channel (see TH1 documentation)}
void AddVariablesArray(const TString &expression, int size, char type='F', Double_t min=0, Double_t max=0)
user inserts discriminating array of variables in data set info in case input tree provides an array ...
void AddSignalTree(TTree *signal, Double_t weight=1.0, Types::ETreeType treetype=Types::kMaxTreeType)
number of signal events (used to compute significance)
void PrepareTrainingAndTestTree(const TCut &cut, const TString &splitOpt)
prepare the training and test trees -> same cuts for signal and background
void AddBackgroundTree(TTree *background, Double_t weight=1.0, Types::ETreeType treetype=Types::kMaxTreeType)
number of signal events (used to compute significance)
This is the main MVA steering class.
static void PyInitialize()
Initialize Python interpreter.
Class supporting a collection of lines with C++ code.
virtual Double_t Gaus(Double_t mean=0, Double_t sigma=1)
Samples a random number from the standard Normal (Gaussian) Distribution with the given mean and sigm...
virtual void SetSeed(ULong_t seed=0)
Set the random generator seed.
virtual Double_t Uniform(Double_t x1=1)
Returns a uniform deviate on the interval (0, x1).
const char * Data() const
static TString Format(const char *fmt,...)
Static method which formats a string using a printf style format descriptor and return a TString.
virtual Int_t Exec(const char *shellcmd)
Execute a command.
virtual Bool_t AccessPathName(const char *path, EAccessMode mode=kFileExists)
Returns FALSE if one can access a file using the specified access mode.
virtual void Setenv(const char *name, const char *value)
Set environment variable.
A TTree represents a columnar dataset.
virtual Long64_t GetEntries() const
void EnableImplicitMT(UInt_t numthreads=0)
Enable ROOT's implicit multi-threading for all objects and methods that provide an internal paralleli...
UInt_t GetThreadPoolSize()
Returns the size of ROOT's thread pool.