DataSetInfo : [dataset] : Added class "Signal"
: Add Tree sig_tree of type Signal with 1000 events
DataSetInfo : [dataset] : Added class "Background"
: Add Tree bkg_tree of type Background with 1000 events
Factory : Booking method: ␛[1mBDT␛[0m
:
: Rebuilding Dataset dataset
: 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 : 800
: Signal -- testing events : 200
: Signal -- training and testing events: 1000
: Background -- training events : 800
: Background -- testing events : 200
: Background -- training and testing events: 1000
:
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,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.,MaxEpochs=10: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,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.,MaxEpochs=10: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,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.,MaxEpochs=10" [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,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0,MaxEpochs=10: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,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0,MaxEpochs=10: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,WeightDecay=1e-4,Regularization=None,Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0,MaxEpochs=10" [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 : Booking method: ␛[1mPyTorch␛[0m
:
: Using PyTorch - setting special configuration options
: Using PyTorch version 1
: Setup PyTorch Model for training
: Executing user initialization code from /home/sftnight/build/workspace/root-makedoc-master/rootspi/rdoc/src/master.build/tutorials/tmva/PyTorch_Generate_CNN_Model.py
Running with nthreads = 4
running Torch code defining the model....
The PyTorch CNN model is created and saved as PyTorchModelCNN.pt
: Loaded pytorch train function:
: Loaded pytorch optimizer:
: Loaded pytorch loss function:
: Loaded pytorch predict function:
: Loaded model from file: PyTorchModelCNN.pt
custom objects for loading model : {'optimizer': <class 'torch.optim.adam.Adam'>, 'criterion': BCELoss(), 'train_func': <function fit at 0x7f7bcf9e0040>, 'predict_func': <function predict at 0x7f7bcf9e00d0>}
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
reshape (Reshape) (None, 16, 16, 1) 0
conv2d (Conv2D) (None, 16, 16, 10) 100
conv2d_1 (Conv2D) (None, 16, 16, 10) 910
max_pooling2d (MaxPooling2D (None, 8, 8, 10) 0
)
flatten (Flatten) (None, 640) 0
dense (Dense) (None, 64) 41024
dense_1 (Dense) (None, 2) 130
=================================================================
Total params: 42,164
Trainable params: 42,164
Non-trainable params: 0
_________________________________________________________________
Factory : Booking method: ␛[1mPyKeras␛[0m
:
: Setting up tf.keras
: Using TensorFlow version 2
: Use Keras version from TensorFlow : tf.keras
: Applying GPU option: gpu_options.allow_growth=True
: Loading Keras Model
: Loaded model from file: model_cnn.h5
Factory : ␛[1mTrain all methods␛[0m
Factory : Train method: BDT for Classification
:
BDT : #events: (reweighted) sig: 800 bkg: 800
: #events: (unweighted) sig: 800 bkg: 800
: Training 400 Decision Trees ... patience please
: Elapsed time for training with 1600 events: 1.66 sec
BDT : [dataset] : Evaluation of BDT on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.0402 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 = 4
:
: ***** 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 1280 events for training and 320 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 | 1.20998 1.05391 0.180705 0.0159379 7283 0
: 2 Minimum Test error found - save the configuration
: 2 | 0.724207 0.929779 0.179681 0.0156885 7317.41 0
: 3 Minimum Test error found - save the configuration
: 3 | 0.633575 0.859455 0.179518 0.015633 7322.19 0
: 4 Minimum Test error found - save the configuration
: 4 | 0.561124 0.761845 0.184553 0.0158233 7111.98 0
: 5 Minimum Test error found - save the configuration
: 5 | 0.483289 0.725782 0.179832 0.0157844 7314.95 0
: 6 | 0.421968 0.742091 0.178994 0.0150177 7318.13 1
: 7 | 0.406054 0.836856 0.179571 0.0151418 7297.96 2
: 8 | 0.349026 0.772862 0.179291 0.0150292 7305.42 3
: 9 | 0.285144 0.756626 0.18152 0.0154451 7225.65 4
: 10 | 0.276912 0.730814 0.182177 0.0151286 7183.53 5
:
: Elapsed time for training with 1600 events: 1.85 sec
: Evaluate deep neural network on CPU using batches with size = 100
:
TMVA_DNN_CPU : [dataset] : Evaluation of TMVA_DNN_CPU on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.0797 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 = 4
:
: ***** 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 1280 events for training and 320 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 | 2.72363 0.782774 1.46189 0.116153 891.707 0
: 2 Minimum Test error found - save the configuration
: 2 | 0.813984 0.739156 1.43998 0.113416 904.595 0
: 3 | 0.745331 0.776283 1.44198 0.110265 901.096 1
: 4 Minimum Test error found - save the configuration
: 4 | 0.704638 0.717018 1.44163 0.113153 903.289 0
: 5 Minimum Test error found - save the configuration
: 5 | 0.659612 0.675979 1.44032 0.113058 904.115 0
: 6 Minimum Test error found - save the configuration
: 6 | 0.613388 0.673139 1.44186 0.113481 903.357 0
: 7 Minimum Test error found - save the configuration
: 7 | 0.586098 0.654411 1.43594 0.112096 906.453 0
: 8 Minimum Test error found - save the configuration
: 8 | 0.565368 0.63537 1.42963 0.112273 910.915 0
: 9 | 0.526173 0.642534 1.43061 0.109998 908.67 1
: 10 | 0.533928 0.660939 1.43842 0.110836 903.899 2
:
: Elapsed time for training with 1600 events: 14.5 sec
: Evaluate deep neural network on CPU using batches with size = 100
:
TMVA_CNN_CPU : [dataset] : Evaluation of TMVA_CNN_CPU on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.585 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
:
Factory : Train method: PyTorch for Classification
:
:
: ␛[1m================================================================␛[0m
: ␛[1mH e l p f o r M V A m e t h o d [ PyTorch ] :␛[0m
:
: PyTorch is a scientific computing package supporting
: automatic differentiation. This method wraps the training
: and predictions steps of the PyTorch Python package for
: TMVA, so that dataloading, preprocessing and evaluation
: can be done within the TMVA system. To use this PyTorch
: interface, you need to generatea model with PyTorch first.
: Then, this model can be loaded and trained in TMVA.
:
:
: <Suppress this message by specifying "!H" in the booking option>
: ␛[1m================================================================␛[0m
:
: Split TMVA training data in 1280 training events and 320 validation events
: Print Training Model Architecture
: Option SaveBestOnly: Only model weights with smallest validation loss will be stored
: Elapsed time for training with 1600 events: 22.1 sec
PyTorch : [dataset] : Evaluation of PyTorch on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.417 sec
: Creating xml weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_PyTorch.weights.xml␛[0m
: Creating standalone class: ␛[0;36mdataset/weights/TMVA_CNN_Classification_PyTorch.class.C␛[0m
Factory : Training finished
:
Factory : Train method: PyKeras for Classification
:
:
: ␛[1m================================================================␛[0m
: ␛[1mH e l p f o r M V A m e t h o d [ PyKeras ] :␛[0m
:
: Keras is a high-level API for the Theano and Tensorflow packages.
: This method wraps the training and predictions steps of the Keras
: Python package for TMVA, so that dataloading, preprocessing and
: evaluation can be done within the TMVA system. To use this Keras
: interface, you have to generate a model with Keras first. Then,
: this model can be loaded and trained in TMVA.
:
:
: <Suppress this message by specifying "!H" in the booking option>
: ␛[1m================================================================␛[0m
:
: Split TMVA training data in 1280 training events and 320 validation events
: Training Model Summary
RecursiveScriptModule(
original_name=Sequential
(0): RecursiveScriptModule(original_name=Reshape)
(1): RecursiveScriptModule(original_name=Conv2d)
(2): RecursiveScriptModule(original_name=ReLU)
(3): RecursiveScriptModule(original_name=BatchNorm2d)
(4): RecursiveScriptModule(original_name=Conv2d)
(5): RecursiveScriptModule(original_name=ReLU)
(6): RecursiveScriptModule(original_name=MaxPool2d)
(7): RecursiveScriptModule(original_name=Flatten)
(8): RecursiveScriptModule(original_name=Linear)
(9): RecursiveScriptModule(original_name=ReLU)
(10): RecursiveScriptModule(original_name=Linear)
(11): RecursiveScriptModule(original_name=Sigmoid)
)
[1, 4] train loss: 1.027
[1, 8] train loss: 0.736
[1, 12] train loss: 0.715
[1] val loss: 0.709
[2, 4] train loss: 0.693
[2, 8] train loss: 0.687
[2, 12] train loss: 0.700
[2] val loss: 0.689
[3, 4] train loss: 0.677
[3, 8] train loss: 0.687
[3, 12] train loss: 0.677
[3] val loss: 0.684
[4, 4] train loss: 0.660
[4, 8] train loss: 0.665
[4, 12] train loss: 0.658
[4] val loss: 0.732
[5, 4] train loss: 0.656
[5, 8] train loss: 0.636
[5, 12] train loss: 0.658
[5] val loss: 0.716
[6, 4] train loss: 0.595
[6, 8] train loss: 0.605
[6, 12] train loss: 0.605
[6] val loss: 0.692
[7, 4] train loss: 0.578
[7, 8] train loss: 0.547
[7, 12] train loss: 0.593
[7] val loss: 0.675
[8, 4] train loss: 0.539
[8, 8] train loss: 0.539
[8, 12] train loss: 0.481
[8] val loss: 0.693
[9, 4] train loss: 0.458
[9, 8] train loss: 0.403
[9, 12] train loss: 0.377
[9] val loss: 0.647
[10, 4] train loss: 0.411
[10, 8] train loss: 0.409
[10, 12] train loss: 0.525
[10] val loss: 0.933
Finished Training on 10 Epochs!
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
reshape (Reshape) (None, 16, 16, 1) 0
conv2d (Conv2D) (None, 16, 16, 10) 100
conv2d_1 (Conv2D) (None, 16, 16, 10) 910
max_pooling2d (MaxPooling2D (None, 8, 8, 10) 0
)
flatten (Flatten) (None, 640) 0
dense (Dense) (None, 64) 41024
dense_1 (Dense) (None, 2) 130
=================================================================
Total params: 42,164
Trainable params: 42,164
Non-trainable params: 0
_________________________________________________________________
: Option SaveBestOnly: Only model weights with smallest validation loss will be stored
Epoch 1/10
1/13 [=>............................] - ETA: 9s - loss: 0.8127 - accuracy: 0.4800␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.7558 - accuracy: 0.4920␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
11/13 [========================>.....] - ETA: 0s - loss: 0.7290 - accuracy: 0.4955
Epoch 1: val_loss improved from inf to 0.69625, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 1s 54ms/step - loss: 0.7241 - accuracy: 0.5023 - val_loss: 0.6962 - val_accuracy: 0.4812
Epoch 2/10
1/13 [=>............................] - ETA: 0s - loss: 0.6940 - accuracy: 0.4900␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
7/13 [===============>..............] - ETA: 0s - loss: 0.6897 - accuracy: 0.5500
Epoch 2: val_loss did not improve from 0.69625
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 12ms/step - loss: 0.6927 - accuracy: 0.5336 - val_loss: 0.7038 - val_accuracy: 0.4719
Epoch 3/10
1/13 [=>............................] - ETA: 0s - loss: 0.6865 - accuracy: 0.5300␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.6928 - accuracy: 0.5400
Epoch 3: val_loss improved from 0.69625 to 0.68637, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 13ms/step - loss: 0.6897 - accuracy: 0.5344 - val_loss: 0.6864 - val_accuracy: 0.5312
Epoch 4/10
1/13 [=>............................] - ETA: 0s - loss: 0.6814 - accuracy: 0.5200␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
7/13 [===============>..............] - ETA: 0s - loss: 0.6798 - accuracy: 0.5757
Epoch 4: val_loss improved from 0.68637 to 0.68222, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 15ms/step - loss: 0.6809 - accuracy: 0.5539 - val_loss: 0.6822 - val_accuracy: 0.5969
Epoch 5/10
1/13 [=>............................] - ETA: 0s - loss: 0.6809 - accuracy: 0.6000␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.6676 - accuracy: 0.6087
Epoch 5: val_loss improved from 0.68222 to 0.67945, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 14ms/step - loss: 0.6715 - accuracy: 0.5961 - val_loss: 0.6794 - val_accuracy: 0.5594
Epoch 6/10
1/13 [=>............................] - ETA: 0s - loss: 0.6643 - accuracy: 0.6600␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.6640 - accuracy: 0.6125
Epoch 6: val_loss improved from 0.67945 to 0.67893, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 15ms/step - loss: 0.6628 - accuracy: 0.6070 - val_loss: 0.6789 - val_accuracy: 0.6000
Epoch 7/10
1/13 [=>............................] - ETA: 0s - loss: 0.6484 - accuracy: 0.7000␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.6435 - accuracy: 0.6775
Epoch 7: val_loss improved from 0.67893 to 0.66773, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 15ms/step - loss: 0.6466 - accuracy: 0.6602 - val_loss: 0.6677 - val_accuracy: 0.6094
Epoch 8/10
1/13 [=>............................] - ETA: 0s - loss: 0.6469 - accuracy: 0.6800␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.6314 - accuracy: 0.6875
Epoch 8: val_loss did not improve from 0.66773
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 13ms/step - loss: 0.6245 - accuracy: 0.6969 - val_loss: 0.6756 - val_accuracy: 0.5938
Epoch 9/10
1/13 [=>............................] - ETA: 0s - loss: 0.5547 - accuracy: 0.7800␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.6069 - accuracy: 0.7075
Epoch 9: val_loss improved from 0.66773 to 0.66753, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 14ms/step - loss: 0.6018 - accuracy: 0.7109 - val_loss: 0.6675 - val_accuracy: 0.5750
Epoch 10/10
1/13 [=>............................] - ETA: 0s - loss: 0.5905 - accuracy: 0.7300␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
7/13 [===============>..............] - ETA: 0s - loss: 0.5827 - accuracy: 0.7214
Epoch 10: val_loss improved from 0.66753 to 0.64470, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 15ms/step - loss: 0.5678 - accuracy: 0.7437 - val_loss: 0.6447 - val_accuracy: 0.6344
: Getting training history for item:0 name = 'loss'
: Getting training history for item:1 name = 'accuracy'
: Getting training history for item:2 name = 'val_loss'
: Getting training history for item:3 name = 'val_accuracy'
: Elapsed time for training with 1600 events: 3.68 sec
: Setting up tf.keras
: Using TensorFlow version 2
: Use Keras version from TensorFlow : tf.keras
: Applying GPU option: gpu_options.allow_growth=True
: Disabled TF eager execution when evaluating model
: Loading Keras Model
: Loaded model from file: trained_model_cnn.h5
PyKeras : [dataset] : Evaluation of PyKeras on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.152 sec
: Creating xml weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_PyKeras.weights.xml␛[0m
: Creating standalone class: ␛[0;36mdataset/weights/TMVA_CNN_Classification_PyKeras.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 : 9.186e-03
: 2 : vars : 8.519e-03
: 3 : vars : 8.403e-03
: 4 : vars : 8.362e-03
: 5 : vars : 8.307e-03
: 6 : vars : 7.765e-03
: 7 : vars : 7.681e-03
: 8 : vars : 7.622e-03
: 9 : vars : 7.418e-03
: 10 : vars : 7.244e-03
: 11 : vars : 7.054e-03
: 12 : vars : 6.970e-03
: 13 : vars : 6.941e-03
: 14 : vars : 6.821e-03
: 15 : vars : 6.802e-03
: 16 : vars : 6.780e-03
: 17 : vars : 6.650e-03
: 18 : vars : 6.584e-03
: 19 : vars : 6.506e-03
: 20 : vars : 6.450e-03
: 21 : vars : 6.447e-03
: 22 : vars : 6.290e-03
: 23 : vars : 6.284e-03
: 24 : vars : 6.273e-03
: 25 : vars : 6.260e-03
: 26 : vars : 6.257e-03
: 27 : vars : 6.248e-03
: 28 : vars : 6.242e-03
: 29 : vars : 6.198e-03
: 30 : vars : 6.173e-03
: 31 : vars : 6.147e-03
: 32 : vars : 6.089e-03
: 33 : vars : 5.931e-03
: 34 : vars : 5.911e-03
: 35 : vars : 5.907e-03
: 36 : vars : 5.904e-03
: 37 : vars : 5.878e-03
: 38 : vars : 5.847e-03
: 39 : vars : 5.826e-03
: 40 : vars : 5.819e-03
: 41 : vars : 5.818e-03
: 42 : vars : 5.794e-03
: 43 : vars : 5.743e-03
: 44 : vars : 5.714e-03
: 45 : vars : 5.704e-03
: 46 : vars : 5.659e-03
: 47 : vars : 5.652e-03
: 48 : vars : 5.634e-03
: 49 : vars : 5.617e-03
: 50 : vars : 5.616e-03
: 51 : vars : 5.603e-03
: 52 : vars : 5.602e-03
: 53 : vars : 5.590e-03
: 54 : vars : 5.566e-03
: 55 : vars : 5.534e-03
: 56 : vars : 5.524e-03
: 57 : vars : 5.521e-03
: 58 : vars : 5.479e-03
: 59 : vars : 5.438e-03
: 60 : vars : 5.435e-03
: 61 : vars : 5.419e-03
: 62 : vars : 5.309e-03
: 63 : vars : 5.293e-03
: 64 : vars : 5.285e-03
: 65 : vars : 5.265e-03
: 66 : vars : 5.253e-03
: 67 : vars : 5.247e-03
: 68 : vars : 5.246e-03
: 69 : vars : 5.217e-03
: 70 : vars : 5.197e-03
: 71 : vars : 5.192e-03
: 72 : vars : 5.186e-03
: 73 : vars : 5.177e-03
: 74 : vars : 5.138e-03
: 75 : vars : 5.125e-03
: 76 : vars : 5.088e-03
: 77 : vars : 5.073e-03
: 78 : vars : 5.064e-03
: 79 : vars : 5.055e-03
: 80 : vars : 5.035e-03
: 81 : vars : 5.024e-03
: 82 : vars : 5.016e-03
: 83 : vars : 4.961e-03
: 84 : vars : 4.889e-03
: 85 : vars : 4.889e-03
: 86 : vars : 4.872e-03
: 87 : vars : 4.866e-03
: 88 : vars : 4.858e-03
: 89 : vars : 4.813e-03
: 90 : vars : 4.800e-03
: 91 : vars : 4.786e-03
: 92 : vars : 4.783e-03
: 93 : vars : 4.767e-03
: 94 : vars : 4.744e-03
: 95 : vars : 4.728e-03
: 96 : vars : 4.720e-03
: 97 : vars : 4.690e-03
: 98 : vars : 4.671e-03
: 99 : vars : 4.669e-03
: 100 : vars : 4.613e-03
: 101 : vars : 4.569e-03
: 102 : vars : 4.547e-03
: 103 : vars : 4.522e-03
: 104 : vars : 4.459e-03
: 105 : vars : 4.422e-03
: 106 : vars : 4.324e-03
: 107 : vars : 4.323e-03
: 108 : vars : 4.323e-03
: 109 : vars : 4.302e-03
: 110 : vars : 4.295e-03
: 111 : vars : 4.265e-03
: 112 : vars : 4.250e-03
: 113 : vars : 4.231e-03
: 114 : vars : 4.175e-03
: 115 : vars : 4.174e-03
: 116 : vars : 4.132e-03
: 117 : vars : 4.093e-03
: 118 : vars : 4.060e-03
: 119 : vars : 4.054e-03
: 120 : vars : 4.046e-03
: 121 : vars : 4.022e-03
: 122 : vars : 4.013e-03
: 123 : vars : 4.012e-03
: 124 : vars : 3.981e-03
: 125 : vars : 3.936e-03
: 126 : vars : 3.909e-03
: 127 : vars : 3.882e-03
: 128 : vars : 3.850e-03
: 129 : vars : 3.844e-03
: 130 : vars : 3.840e-03
: 131 : vars : 3.823e-03
: 132 : vars : 3.806e-03
: 133 : vars : 3.780e-03
: 134 : vars : 3.777e-03
: 135 : vars : 3.776e-03
: 136 : vars : 3.765e-03
: 137 : vars : 3.761e-03
: 138 : vars : 3.722e-03
: 139 : vars : 3.704e-03
: 140 : vars : 3.673e-03
: 141 : vars : 3.662e-03
: 142 : vars : 3.647e-03
: 143 : vars : 3.640e-03
: 144 : vars : 3.638e-03
: 145 : vars : 3.559e-03
: 146 : vars : 3.546e-03
: 147 : vars : 3.544e-03
: 148 : vars : 3.519e-03
: 149 : vars : 3.501e-03
: 150 : vars : 3.489e-03
: 151 : vars : 3.474e-03
: 152 : vars : 3.452e-03
: 153 : vars : 3.443e-03
: 154 : vars : 3.442e-03
: 155 : vars : 3.421e-03
: 156 : vars : 3.394e-03
: 157 : vars : 3.359e-03
: 158 : vars : 3.336e-03
: 159 : vars : 3.334e-03
: 160 : vars : 3.287e-03
: 161 : vars : 3.267e-03
: 162 : vars : 3.246e-03
: 163 : vars : 3.235e-03
: 164 : vars : 3.213e-03
: 165 : vars : 3.208e-03
: 166 : vars : 3.208e-03
: 167 : vars : 3.173e-03
: 168 : vars : 3.138e-03
: 169 : vars : 3.132e-03
: 170 : vars : 3.085e-03
: 171 : vars : 3.083e-03
: 172 : vars : 3.074e-03
: 173 : vars : 3.068e-03
: 174 : vars : 3.057e-03
: 175 : vars : 3.047e-03
: 176 : vars : 3.034e-03
: 177 : vars : 3.028e-03
: 178 : vars : 3.017e-03
: 179 : vars : 2.990e-03
: 180 : vars : 2.969e-03
: 181 : vars : 2.965e-03
: 182 : vars : 2.963e-03
: 183 : vars : 2.953e-03
: 184 : vars : 2.943e-03
: 185 : vars : 2.899e-03
: 186 : vars : 2.891e-03
: 187 : vars : 2.833e-03
: 188 : vars : 2.820e-03
: 189 : vars : 2.765e-03
: 190 : vars : 2.748e-03
: 191 : vars : 2.740e-03
: 192 : vars : 2.717e-03
: 193 : vars : 2.710e-03
: 194 : vars : 2.678e-03
: 195 : vars : 2.611e-03
: 196 : vars : 2.539e-03
: 197 : vars : 2.511e-03
: 198 : vars : 2.490e-03
: 199 : vars : 2.478e-03
: 200 : vars : 2.433e-03
: 201 : vars : 2.393e-03
: 202 : vars : 2.359e-03
: 203 : vars : 2.354e-03
: 204 : vars : 2.305e-03
: 205 : vars : 2.267e-03
: 206 : vars : 2.250e-03
: 207 : vars : 2.244e-03
: 208 : vars : 2.195e-03
: 209 : vars : 2.158e-03
: 210 : vars : 2.127e-03
: 211 : vars : 2.104e-03
: 212 : vars : 2.090e-03
: 213 : vars : 1.976e-03
: 214 : vars : 1.964e-03
: 215 : vars : 1.927e-03
: 216 : vars : 1.892e-03
: 217 : vars : 1.838e-03
: 218 : vars : 1.828e-03
: 219 : vars : 1.761e-03
: 220 : vars : 1.754e-03
: 221 : vars : 1.751e-03
: 222 : vars : 1.719e-03
: 223 : vars : 1.678e-03
: 224 : vars : 1.606e-03
: 225 : vars : 1.529e-03
: 226 : vars : 1.519e-03
: 227 : vars : 1.501e-03
: 228 : vars : 1.492e-03
: 229 : vars : 1.426e-03
: 230 : vars : 1.400e-03
: 231 : vars : 1.372e-03
: 232 : vars : 1.355e-03
: 233 : vars : 1.346e-03
: 234 : vars : 1.245e-03
: 235 : vars : 1.174e-03
: 236 : vars : 1.095e-03
: 237 : vars : 1.064e-03
: 238 : vars : 1.010e-03
: 239 : vars : 8.799e-04
: 240 : vars : 5.093e-04
: 241 : vars : 1.931e-04
: 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
: No variable ranking supplied by classifier: PyTorch
: No variable ranking supplied by classifier: PyKeras
TH1.Print Name = TrainingHistory_TMVA_DNN_CPU_trainingError, Entries= 0, Total sum= 5.35128
TH1.Print Name = TrainingHistory_TMVA_DNN_CPU_valError, Entries= 0, Total sum= 8.17002
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_trainingError, Entries= 0, Total sum= 8.47215
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_valError, Entries= 0, Total sum= 6.9576
TH1.Print Name = TrainingHistory_PyKeras_'accuracy', Entries= 0, Total sum= 6.13906
TH1.Print Name = TrainingHistory_PyKeras_'loss', Entries= 0, Total sum= 6.56255
TH1.Print Name = TrainingHistory_PyKeras_'val_accuracy', Entries= 0, Total sum= 5.65312
TH1.Print Name = TrainingHistory_PyKeras_'val_loss', Entries= 0, Total sum= 6.78261
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
: Reading weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_PyTorch.weights.xml␛[0m
: Reading weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_PyKeras.weights.xml␛[0m
Factory : ␛[1mTest all methods␛[0m
Factory : Test method: BDT for Classification performance
:
BDT : [dataset] : Evaluation of BDT on testing sample (400 events)
: Elapsed time for evaluation of 400 events: 0.0112 sec
Factory : Test method: TMVA_DNN_CPU for Classification performance
:
: Evaluate deep neural network on CPU using batches with size = 400
:
TMVA_DNN_CPU : [dataset] : Evaluation of TMVA_DNN_CPU on testing sample (400 events)
: Elapsed time for evaluation of 400 events: 0.0188 sec
Factory : Test method: TMVA_CNN_CPU for Classification performance
:
: Evaluate deep neural network on CPU using batches with size = 400
:
TMVA_CNN_CPU : [dataset] : Evaluation of TMVA_CNN_CPU on testing sample (400 events)
: Elapsed time for evaluation of 400 events: 0.155 sec
Factory : Test method: PyTorch for Classification performance
:
: Setup PyTorch Model for training
: Executing user initialization code from /home/sftnight/build/workspace/root-makedoc-master/rootspi/rdoc/src/master.build/tutorials/tmva/PyTorch_Generate_CNN_Model.py
running Torch code defining the model....
The PyTorch CNN model is created and saved as PyTorchModelCNN.pt
: Loaded pytorch train function:
: Loaded pytorch optimizer:
: Loaded pytorch loss function:
: Loaded pytorch predict function:
: Loaded model from file: PyTorchTrainedModelCNN.pt
PyTorch : [dataset] : Evaluation of PyTorch on testing sample (400 events)
: Elapsed time for evaluation of 400 events: 0.122 sec
Factory : Test method: PyKeras for Classification performance
:
: Setting up tf.keras
: Using TensorFlow version 2
: Use Keras version from TensorFlow : tf.keras
: Applying GPU option: gpu_options.allow_growth=True
: Disabled TF eager execution when evaluating model
: Loading Keras Model
: Loaded model from file: trained_model_cnn.h5
PyKeras : [dataset] : Evaluation of PyKeras on testing sample (400 events)
: Elapsed time for evaluation of 400 events: 0.0969 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
Factory : Evaluate classifier: PyTorch
:
PyTorch : [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: PyKeras
:
PyKeras : [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
:
: Evaluation results ranked by best signal efficiency and purity (area)
: -------------------------------------------------------------------------------------------------------------------
: DataSet MVA
: Name: Method: ROC-integ
: dataset PyTorch : 0.834
: dataset BDT : 0.781
: dataset TMVA_CNN_CPU : 0.718
: dataset PyKeras : 0.641
: dataset TMVA_DNN_CPU : 0.603
: -------------------------------------------------------------------------------------------------------------------
:
: 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 PyTorch : 0.045 (0.305) 0.585 (0.713) 0.790 (0.926)
: dataset BDT : 0.135 (0.325) 0.365 (0.752) 0.751 (0.901)
: dataset TMVA_CNN_CPU : 0.035 (0.115) 0.315 (0.476) 0.638 (0.742)
: dataset PyKeras : 0.030 (0.075) 0.189 (0.361) 0.470 (0.713)
: dataset TMVA_DNN_CPU : 0.025 (0.105) 0.200 (0.402) 0.409 (0.681)
: -------------------------------------------------------------------------------------------------------------------
:
Dataset:dataset : Created tree 'TestTree' with 400 events
:
Dataset:dataset : Created tree 'TrainTree' with 1600 events
:
Factory : ␛[1mThank you for using TMVA!␛[0m
: ␛[1mFor citation information, please visit: http://tmva.sf.net/citeTMVA.html␛[0m
custom objects for loading model : {'optimizer': <class 'torch.optim.adam.Adam'>, 'criterion': BCELoss(), 'train_func': <function fit at 0x7f7b44045a60>, 'predict_func': <function predict at 0x7f7b44045c10>}
import ROOT
ROOT.gSystem.Setenv("OMP_NUM_THREADS", "1")
TMVA = ROOT.TMVA
TFile = ROOT.TFile
import os
import importlib
def MakeImagesTree(n, nh, nw):
ntot = nh * nw
fileOutName = "images_data_16x16.root"
nRndmEvts = 10000
delta_sigma = 0.1
pixelNoise = 5
sX1 = 3
sY1 = 3
sX2 = sX1 + delta_sigma
sY2 = sY1 - delta_sigma
h1 = ROOT.TH2D("h1", "h1", nh, 0, 10, nw, 0, 10)
h2 = ROOT.TH2D("h2", "h2", nh, 0, 10, nw, 0, 10)
f1 = ROOT.TF2("f1", "xygaus")
f2 = ROOT.TF2("f2", "xygaus")
sgn = ROOT.TTree("sig_tree", "signal_tree")
bkg = ROOT.TTree("bkg_tree", "background_tree")
f =
TFile(fileOutName,
"RECREATE")
x1 = ROOT.std.vector["float"](ntot)
x2 = ROOT.std.vector["float"](ntot)
bkg.Branch("vars", "std::vector<float>", x1)
sgn.Branch("vars", "std::vector<float>", x2)
sgn.SetDirectory(f)
bkg.SetDirectory(f)
f1.SetParameters(1, 5, sX1, 5, sY1)
f2.SetParameters(1, 5, sX2, 5, sY2)
ROOT.gRandom.SetSeed(0)
ROOT.Info("TMVA_CNN_Classification", "Filling ROOT tree \n")
for i in range(n):
if i % 1000 == 0:
print("Generating image event ...", i)
h1.Reset()
h2.Reset()
f1.SetParameter(1, ROOT.gRandom.Uniform(3, 7))
f1.SetParameter(3, ROOT.gRandom.Uniform(3, 7))
f2.SetParameter(1, ROOT.gRandom.Uniform(3, 7))
f2.SetParameter(3, ROOT.gRandom.Uniform(3, 7))
h1.FillRandom("f1", nRndmEvts)
h2.FillRandom("f2", nRndmEvts)
for k in range(nh):
for l in range(nw):
m = k * nw + l
x1[m] = h1.GetBinContent(k + 1, l + 1) + ROOT.gRandom.Gaus(0, pixelNoise)
x2[m] = h2.GetBinContent(k + 1, l + 1) + ROOT.gRandom.Gaus(0, pixelNoise)
sgn.Fill()
bkg.Fill()
sgn.Write()
bkg.Write()
print("Signal and background tree with images data written to the file %s", f.GetName())
sgn.Print()
bkg.Print()
f.Close()
hasGPU = ROOT.gSystem.GetFromPipe("root-config --has-tmva-gpu") == "yes"
hasCPU = ROOT.gSystem.GetFromPipe("root-config --has-tmva-cpu") == "yes"
nevt = 1000
opt = [1, 1, 1, 1, 1]
useTMVACNN = opt[0]
if len(opt) > 0
else False
useKerasCNN = opt[1]
if len(opt) > 1
else False
useTMVADNN = opt[2]
if len(opt) > 2
else False
useTMVABDT = opt[3]
if len(opt) > 3
else False
usePyTorchCNN = opt[4]
if len(opt) > 4
else False
if (not hasCPU and not hasGPU) :
ROOT.Warning("TMVA_CNN_Classificaton","ROOT is not supporting tmva-cpu and tmva-gpu skip using TMVA-DNN and TMVA-CNN")
useTMVACNN = False
useTMVADNN = False
if ROOT.gSystem.GetFromPipe("root-config --has-tmva-pymva") != "yes":
useKerasCNN = False
usePyTorchCNN = False
else:
tf_spec = importlib.util.find_spec("tensorflow")
if tf_spec is None:
useKerasCNN = False
ROOT.Warning("TMVA_CNN_Classificaton","Skip using Keras since tensorflow is not installed")
torch_spec = importlib.util.find_spec("torch")
if torch_spec is None:
usePyTorchCNN = False
ROOT.Warning("TMVA_CNN_Classificaton","Skip using PyTorch since torch is not installed")
if not useTMVACNN:
ROOT.Warning(
"TMVA_CNN_Classificaton",
"TMVA is not build with GPU or CPU multi-thread support. Cannot use TMVA Deep Learning for CNN",
)
writeOutputFile = True
num_threads = 4
max_epochs = 10
if num_threads >= 0:
outputFile = None
if writeOutputFile:
outputFile =
TFile.Open(
"TMVA_CNN_ClassificationOutput.root",
"RECREATE")
"TMVA_CNN_Classification",
outputFile,
V=False,
ROC=True,
Silent=False,
Color=True,
AnalysisType="Classification",
Transformations=None,
Correlations=False,
)
imgSize = 16 * 16
inputFileName = "images_data_16x16.root"
if ROOT.gSystem.AccessPathName(inputFileName):
MakeImagesTree(nevt, 16, 16)
if inputFile is None:
ROOT.Warning("TMVA_CNN_Classification", "Error opening input file %s - exit", inputFileName.Data())
signalTree = inputFile.Get("sig_tree")
backgroundTree = inputFile.Get("bkg_tree")
nEventsSig = signalTree.GetEntries()
nEventsBkg = backgroundTree.GetEntries()
signalWeight = 1.0
backgroundWeight = 1.0
loader.AddSignalTree(signalTree, signalWeight)
loader.AddBackgroundTree(backgroundTree, backgroundWeight)
loader.AddVariablesArray("vars", imgSize)
mycuts = ""
mycutb = ""
nTrainSig = 0.8 * nEventsSig
nTrainBkg = 0.8 * nEventsBkg
loader.PrepareTrainingAndTestTree(
mycuts,
mycutb,
nTrain_Signal=nTrainSig,
nTrain_Background=nTrainBkg,
SplitMode="Random",
SplitSeed=100,
NormMode="NumEvents",
V=False,
CalcCorrelations=False,
)
if useTMVABDT:
factory.BookMethod(
loader,
TMVA.Types.kBDT,
"BDT",
V=False,
NTrees=400,
MinNodeSize="2.5%",
MaxDepth=2,
BoostType="AdaBoost",
AdaBoostBeta=0.5,
UseBaggedBoost=True,
BaggedSampleFraction=0.5,
SeparationType="GiniIndex",
nCuts=20,
)
if useTMVADNN:
layoutString = ROOT.TString(
"DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,DENSE|1|LINEAR"
)
trainingString1 = ROOT.TString(
"LearningRate=1e-3,Momentum=0.9,Repetitions=1,"
"ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,"
"WeightDecay=1e-4,Regularization=None,"
"Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0."
)
trainingString1 += ",MaxEpochs=" + str(max_epochs)
dnnMethodName = "TMVA_DNN_CPU"
dnnOptions = "CPU"
if hasGPU :
dnnOptions = "GPU"
dnnMethodName = "TMVA_DNN_GPU"
factory.BookMethod(
loader,
TMVA.Types.kDL,
dnnMethodName,
H=False,
V=True,
ErrorStrategy="CROSSENTROPY",
VarTransform=None,
WeightInitialization="XAVIER",
Layout=layoutString,
TrainingStrategy=trainingString1,
Architecture=dnnOptions
)
if useTMVACNN:
trainingString1 = ROOT.TString(
"LearningRate=1e-3,Momentum=0.9,Repetitions=1,"
"ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,"
"WeightDecay=1e-4,Regularization=None,"
"Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0"
)
trainingString1 += ",MaxEpochs=" + str(max_epochs)
cnnMethodName = "TMVA_CNN_CPU"
cnnOptions = "CPU"
if hasGPU:
cnnOptions = "GPU"
cnnMethodName = "TMVA_CNN_GPU"
factory.BookMethod(
loader,
TMVA.Types.kDL,
cnnMethodName,
H=False,
V=True,
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=trainingString1,
Architecture=cnnOptions,
)
if usePyTorchCNN:
ROOT.Info("TMVA_CNN_Classification", "Using Convolutional PyTorch Model")
pyTorchFileName = str(ROOT.gROOT.GetTutorialDir())
pyTorchFileName += "/tmva/PyTorch_Generate_CNN_Model.py"
torch_spec = importlib.util.find_spec("torch")
if torch_spec is not None and os.path.exists(pyTorchFileName):
ROOT.Info("TMVA_CNN_Classification", "Booking PyTorch CNN model")
factory.BookMethod(
loader,
TMVA.Types.kPyTorch,
"PyTorch",
H=True,
V=False,
VarTransform=None,
FilenameModel="PyTorchModelCNN.pt",
FilenameTrainedModel="PyTorchTrainedModelCNN.pt",
NumEpochs=max_epochs,
BatchSize=100,
UserCode=str(pyTorchFileName)
)
else:
ROOT.Warning(
"TMVA_CNN_Classification",
"PyTorch is not installed or model building file is not existing - skip using PyTorch",
)
if useKerasCNN:
ROOT.Info("TMVA_CNN_Classification", "Building convolutional keras model")
import tensorflow
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.layers import Input, Dense, Dropout, Flatten, Conv2D, MaxPooling2D, Reshape
model = Sequential()
model.add(
Reshape((16, 16, 1), input_shape=(256,)))
model.add(Conv2D(10, kernel_size=(3, 3), kernel_initializer="TruncatedNormal", activation="relu", padding="same"))
model.add(Conv2D(10, kernel_size=(3, 3), kernel_initializer="TruncatedNormal", activation="relu", padding="same"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dense(64, activation="tanh"))
model.add(Dense(2, activation="sigmoid"))
model.compile(loss="binary_crossentropy", optimizer=Adam(learning_rate=0.001), weighted_metrics=["accuracy"])
model.save("model_cnn.h5")
model.summary()
if not os.path.exists("model_cnn.h5"):
raise FileNotFoundError("Error creating Keras model file - skip using Keras")
else:
ROOT.Info("TMVA_CNN_Classification", "Booking convolutional keras model")
factory.BookMethod(
loader,
TMVA.Types.kPyKeras,
"PyKeras",
H=True,
V=False,
VarTransform=None,
FilenameModel="model_cnn.h5",
FilenameTrainedModel="trained_model_cnn.h5",
NumEpochs=max_epochs,
BatchSize=100,
GpuOptions="allow_growth=True",
)
factory.TrainAllMethods()
factory.TestAllMethods()
factory.EvaluateAllMethods()
c1 = factory.GetROCCurve(loader)
c1.Draw()
outputFile.Close()
Option_t Option_t TPoint TPoint const char GetTextMagnitude GetFillStyle GetLineColor GetLineWidth GetMarkerStyle GetTextAlign GetTextColor GetTextSize void char Point_t Rectangle_t WindowAttributes_t Float_t Float_t Float_t Int_t Int_t UInt_t UInt_t Rectangle_t Int_t Int_t Window_t TString Int_t GCValues_t GetPrimarySelectionOwner GetDisplay GetScreen GetColormap GetNativeEvent const char const char dpyName wid window const char font_name cursor keysym reg const char only_if_exist regb h Point_t winding char text const char depth char const char Int_t count const char ColorStruct_t color const char Pixmap_t Pixmap_t PictureAttributes_t attr const char char ret_data h unsigned char height h Atom_t Int_t ULong_t ULong_t unsigned char prop_list Atom_t Atom_t Atom_t Time_t UChar_t len
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.
This is the main MVA steering class.
static void PyInitialize()
Initialize Python interpreter.
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.