Running with nthreads = 4
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,MaxEpochs=10,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=10,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=10,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=10,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=10,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=10,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 !
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
reshape (Reshape) (None, 16, 16, 1) 0
conv2d (Conv2D) (None, 16, 16, 10) 100
batch_normalization (Batch (None, 16, 16, 10) 40
Normalization)
conv2d_1 (Conv2D) (None, 16, 16, 10) 910
max_pooling2d (MaxPooling2 (None, 15, 15, 10) 0
D)
flatten (Flatten) (None, 2250) 0
dense (Dense) (None, 256) 576256
dense_1 (Dense) (None, 2) 514
=================================================================
Total params: 577820 (2.20 MB)
Trainable params: 577800 (2.20 MB)
Non-trainable params: 20 (80.00 Byte)
_________________________________________________________________
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 : Booking method: ␛[1mPyTorch␛[0m
:
: Using PyTorch - setting special configuration options
: Using PyTorch version 2
: Setup PyTorch Model for training
: Executing user initialization code from /home/sftnight/build/workspace/root-makedoc-v632/rootspi/rdoc/src/v6-32-00-patches.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: PyTorchModelCNN.pt
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 200 Decision Trees ... patience please
: Elapsed time for training with 1600 events: 0.843 sec
BDT : [dataset] : Evaluation of BDT on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.0166 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 = 46.0465
: --------------------------------------------------------------
: 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 | 0.931312 0.927024 0.179884 0.0159665 7320.74 0
: 2 Minimum Test error found - save the configuration
: 2 | 0.70017 0.765726 0.179016 0.0157244 7348.81 0
: 3 Minimum Test error found - save the configuration
: 3 | 0.620601 0.752244 0.180183 0.0156994 7295.57 0
: 4 | 0.550627 0.767702 0.178523 0.0150716 7341.65 1
: 5 | 0.509858 0.760668 0.17863 0.015081 7337.27 2
: 6 Minimum Test error found - save the configuration
: 6 | 0.447083 0.705682 0.18007 0.0157606 7303.3 0
: 7 | 0.399885 0.717047 0.179667 0.0153552 7303.2 1
: 8 | 0.377543 0.708558 0.178534 0.0150398 7339.69 2
: 9 Minimum Test error found - save the configuration
: 9 | 0.316594 0.674853 0.179061 0.0157213 7346.65 0
: 10 | 0.295116 0.703849 0.178508 0.0150371 7340.76 1
:
: Elapsed time for training with 1600 events: 1.83 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: 0.0791 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 = 101.148
: --------------------------------------------------------------
: 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 | 2.87435 0.780401 1.44315 0.111581 901.19 0
: 2 Minimum Test error found - save the configuration
: 2 | 0.978679 0.716271 1.43736 0.111808 905.285 0
: 3 | 0.760514 0.717947 1.43789 0.109119 903.092 1
: 4 Minimum Test error found - save the configuration
: 4 | 0.71069 0.715045 1.44763 0.111819 898.329 0
: 5 Minimum Test error found - save the configuration
: 5 | 0.682877 0.676852 1.4288 0.110036 909.946 0
: 6 Minimum Test error found - save the configuration
: 6 | 0.653117 0.651654 1.43911 0.112324 904.442 0
: 7 Minimum Test error found - save the configuration
: 7 | 0.636098 0.631942 1.49575 0.140447 885.412 0
: 8 Minimum Test error found - save the configuration
: 8 | 0.615205 0.620584 1.42473 0.111345 913.669 0
: 9 Minimum Test error found - save the configuration
: 9 | 0.593709 0.595247 1.42758 0.110111 910.835 0
: 10 Minimum Test error found - save the configuration
: 10 | 0.564785 0.572599 1.42691 0.112144 912.707 0
:
: 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: 0.587 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: 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
custom objects for loading model : {'optimizer': <class 'torch.optim.adam.Adam'>, 'criterion': BCELoss(), 'train_func': <function fit at 0x7f3339ac2940>, 'predict_func': <function predict at 0x7f3339ac2a60>}
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
reshape (Reshape) (None, 16, 16, 1) 0
conv2d (Conv2D) (None, 16, 16, 10) 100
batch_normalization (Batch (None, 16, 16, 10) 40
Normalization)
conv2d_1 (Conv2D) (None, 16, 16, 10) 910
max_pooling2d (MaxPooling2 (None, 15, 15, 10) 0
D)
flatten (Flatten) (None, 2250) 0
dense (Dense) (None, 256) 576256
dense_1 (Dense) (None, 2) 514
=================================================================
Total params: 577820 (2.20 MB)
Trainable params: 577800 (2.20 MB)
Non-trainable params: 20 (80.00 Byte)
_________________________________________________________________
: Option SaveBestOnly: Only model weights with smallest validation loss will be stored
Epoch 1/10
1/13 [=>............................] - ETA: 10s - loss: 0.8993 - accuracy: 0.5200␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 2.5257 - accuracy: 0.5040 ␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 1.9219 - accuracy: 0.4989␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 1.5794 - accuracy: 0.4961
Epoch 1: val_loss improved from inf to 1.43306, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 1s 50ms/step - loss: 1.5794 - accuracy: 0.4961 - val_loss: 1.4331 - val_accuracy: 0.4719
Epoch 2/10
1/13 [=>............................] - ETA: 0s - loss: 0.8904 - accuracy: 0.4600␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.7500 - accuracy: 0.5220␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.7200 - accuracy: 0.5278␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.7144 - accuracy: 0.5375
Epoch 2: val_loss improved from 1.43306 to 0.86421, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 22ms/step - loss: 0.7144 - accuracy: 0.5375 - val_loss: 0.8642 - val_accuracy: 0.4656
Epoch 3/10
1/13 [=>............................] - ETA: 0s - loss: 0.6864 - accuracy: 0.6400␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.6730 - accuracy: 0.6240␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.6718 - accuracy: 0.6090
Epoch 3: val_loss improved from 0.86421 to 0.72857, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 20ms/step - loss: 0.6720 - accuracy: 0.6117 - val_loss: 0.7286 - val_accuracy: 0.4781
Epoch 4/10
1/13 [=>............................] - ETA: 0s - loss: 0.6807 - accuracy: 0.6200␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
6/13 [============>.................] - ETA: 0s - loss: 0.6557 - accuracy: 0.6433␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.6532 - accuracy: 0.6470
Epoch 4: val_loss did not improve from 0.72857
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 16ms/step - loss: 0.6517 - accuracy: 0.6547 - val_loss: 0.7440 - val_accuracy: 0.4812
Epoch 5/10
1/13 [=>............................] - ETA: 0s - loss: 0.6583 - accuracy: 0.6400␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.6399 - accuracy: 0.6840␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.6317 - accuracy: 0.6960
Epoch 5: val_loss did not improve from 0.72857
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 17ms/step - loss: 0.6320 - accuracy: 0.6828 - val_loss: 0.7377 - val_accuracy: 0.5094
Epoch 6/10
1/13 [=>............................] - ETA: 0s - loss: 0.6256 - accuracy: 0.6600␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
6/13 [============>.................] - ETA: 0s - loss: 0.6102 - accuracy: 0.7233␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
11/13 [========================>.....] - ETA: 0s - loss: 0.6114 - accuracy: 0.7118
Epoch 6: val_loss improved from 0.72857 to 0.69970, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 20ms/step - loss: 0.6143 - accuracy: 0.7039 - val_loss: 0.6997 - val_accuracy: 0.5156
Epoch 7/10
1/13 [=>............................] - ETA: 0s - loss: 0.6007 - accuracy: 0.6900␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.5877 - accuracy: 0.7600␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.5950 - accuracy: 0.7410
Epoch 7: val_loss did not improve from 0.69970
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 16ms/step - loss: 0.5955 - accuracy: 0.7383 - val_loss: 0.7304 - val_accuracy: 0.5156
Epoch 8/10
1/13 [=>............................] - ETA: 0s - loss: 0.5781 - accuracy: 0.7200␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.5886 - accuracy: 0.7180␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.5872 - accuracy: 0.7111
Epoch 8: val_loss improved from 0.69970 to 0.67114, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 20ms/step - loss: 0.5804 - accuracy: 0.7344 - val_loss: 0.6711 - val_accuracy: 0.6156
Epoch 9/10
1/13 [=>............................] - ETA: 0s - loss: 0.5202 - accuracy: 0.8300␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.5395 - accuracy: 0.8020␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.5530 - accuracy: 0.7611␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.5567 - accuracy: 0.7492
Epoch 9: val_loss did not improve from 0.67114
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 18ms/step - loss: 0.5567 - accuracy: 0.7492 - val_loss: 0.6819 - val_accuracy: 0.5437
Epoch 10/10
1/13 [=>............................] - ETA: 0s - loss: 0.5383 - accuracy: 0.7600␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.5328 - accuracy: 0.8020␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.5188 - accuracy: 0.8150
Epoch 10: val_loss did not improve from 0.67114
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 17ms/step - loss: 0.5244 - accuracy: 0.8055 - val_loss: 0.6926 - val_accuracy: 0.5406
: 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: 3.67 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: 0.236 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
:
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: 23.1 sec
PyTorch : [dataset] : Evaluation of PyTorch on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.424 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
:
: Ranking input variables (method specific)...
BDT : Ranking result (top variable is best ranked)
: --------------------------------------
: Rank : Variable : Variable Importance
: --------------------------------------
: 1 : vars : 1.062e-02
: 2 : vars : 1.057e-02
: 3 : vars : 1.055e-02
: 4 : vars : 1.049e-02
: 5 : vars : 9.260e-03
: 6 : vars : 9.104e-03
: 7 : vars : 8.872e-03
: 8 : vars : 8.741e-03
: 9 : vars : 8.343e-03
: 10 : vars : 8.207e-03
: 11 : vars : 8.151e-03
: 12 : vars : 8.108e-03
: 13 : vars : 8.004e-03
: 14 : vars : 7.888e-03
: 15 : vars : 7.574e-03
: 16 : vars : 7.520e-03
: 17 : vars : 7.512e-03
: 18 : vars : 7.496e-03
: 19 : vars : 7.454e-03
: 20 : vars : 7.389e-03
: 21 : vars : 7.297e-03
: 22 : vars : 7.275e-03
: 23 : vars : 7.167e-03
: 24 : vars : 7.141e-03
: 25 : vars : 7.084e-03
: 26 : vars : 7.056e-03
: 27 : vars : 6.999e-03
: 28 : vars : 6.920e-03
: 29 : vars : 6.856e-03
: 30 : vars : 6.829e-03
: 31 : vars : 6.771e-03
: 32 : vars : 6.664e-03
: 33 : vars : 6.605e-03
: 34 : vars : 6.602e-03
: 35 : vars : 6.585e-03
: 36 : vars : 6.562e-03
: 37 : vars : 6.378e-03
: 38 : vars : 6.363e-03
: 39 : vars : 6.318e-03
: 40 : vars : 6.298e-03
: 41 : vars : 6.238e-03
: 42 : vars : 6.219e-03
: 43 : vars : 6.170e-03
: 44 : vars : 6.160e-03
: 45 : vars : 5.976e-03
: 46 : vars : 5.935e-03
: 47 : vars : 5.923e-03
: 48 : vars : 5.911e-03
: 49 : vars : 5.879e-03
: 50 : vars : 5.868e-03
: 51 : vars : 5.854e-03
: 52 : vars : 5.830e-03
: 53 : vars : 5.798e-03
: 54 : vars : 5.796e-03
: 55 : vars : 5.796e-03
: 56 : vars : 5.789e-03
: 57 : vars : 5.773e-03
: 58 : vars : 5.752e-03
: 59 : vars : 5.696e-03
: 60 : vars : 5.657e-03
: 61 : vars : 5.630e-03
: 62 : vars : 5.618e-03
: 63 : vars : 5.612e-03
: 64 : vars : 5.611e-03
: 65 : vars : 5.596e-03
: 66 : vars : 5.549e-03
: 67 : vars : 5.542e-03
: 68 : vars : 5.523e-03
: 69 : vars : 5.520e-03
: 70 : vars : 5.493e-03
: 71 : vars : 5.481e-03
: 72 : vars : 5.459e-03
: 73 : vars : 5.448e-03
: 74 : vars : 5.445e-03
: 75 : vars : 5.421e-03
: 76 : vars : 5.386e-03
: 77 : vars : 5.381e-03
: 78 : vars : 5.376e-03
: 79 : vars : 5.359e-03
: 80 : vars : 5.343e-03
: 81 : vars : 5.324e-03
: 82 : vars : 5.270e-03
: 83 : vars : 5.220e-03
: 84 : vars : 5.216e-03
: 85 : vars : 5.186e-03
: 86 : vars : 5.172e-03
: 87 : vars : 5.167e-03
: 88 : vars : 5.167e-03
: 89 : vars : 5.148e-03
: 90 : vars : 5.141e-03
: 91 : vars : 5.067e-03
: 92 : vars : 5.054e-03
: 93 : vars : 5.009e-03
: 94 : vars : 4.939e-03
: 95 : vars : 4.929e-03
: 96 : vars : 4.924e-03
: 97 : vars : 4.823e-03
: 98 : vars : 4.822e-03
: 99 : vars : 4.816e-03
: 100 : vars : 4.805e-03
: 101 : vars : 4.797e-03
: 102 : vars : 4.768e-03
: 103 : vars : 4.756e-03
: 104 : vars : 4.756e-03
: 105 : vars : 4.746e-03
: 106 : vars : 4.721e-03
: 107 : vars : 4.694e-03
: 108 : vars : 4.694e-03
: 109 : vars : 4.649e-03
: 110 : vars : 4.624e-03
: 111 : vars : 4.598e-03
: 112 : vars : 4.592e-03
: 113 : vars : 4.569e-03
: 114 : vars : 4.512e-03
: 115 : vars : 4.494e-03
: 116 : vars : 4.471e-03
: 117 : vars : 4.442e-03
: 118 : vars : 4.425e-03
: 119 : vars : 4.388e-03
: 120 : vars : 4.382e-03
: 121 : vars : 4.331e-03
: 122 : vars : 4.312e-03
: 123 : vars : 4.301e-03
: 124 : vars : 4.289e-03
: 125 : vars : 4.281e-03
: 126 : vars : 4.198e-03
: 127 : vars : 4.159e-03
: 128 : vars : 4.154e-03
: 129 : vars : 4.146e-03
: 130 : vars : 4.077e-03
: 131 : vars : 4.045e-03
: 132 : vars : 3.989e-03
: 133 : vars : 3.973e-03
: 134 : vars : 3.941e-03
: 135 : vars : 3.938e-03
: 136 : vars : 3.936e-03
: 137 : vars : 3.928e-03
: 138 : vars : 3.894e-03
: 139 : vars : 3.887e-03
: 140 : vars : 3.886e-03
: 141 : vars : 3.869e-03
: 142 : vars : 3.854e-03
: 143 : vars : 3.817e-03
: 144 : vars : 3.746e-03
: 145 : vars : 3.704e-03
: 146 : vars : 3.701e-03
: 147 : vars : 3.687e-03
: 148 : vars : 3.618e-03
: 149 : vars : 3.600e-03
: 150 : vars : 3.600e-03
: 151 : vars : 3.571e-03
: 152 : vars : 3.560e-03
: 153 : vars : 3.524e-03
: 154 : vars : 3.508e-03
: 155 : vars : 3.459e-03
: 156 : vars : 3.441e-03
: 157 : vars : 3.374e-03
: 158 : vars : 3.287e-03
: 159 : vars : 3.283e-03
: 160 : vars : 3.224e-03
: 161 : vars : 3.210e-03
: 162 : vars : 3.171e-03
: 163 : vars : 3.162e-03
: 164 : vars : 3.160e-03
: 165 : vars : 3.158e-03
: 166 : vars : 3.151e-03
: 167 : vars : 3.150e-03
: 168 : vars : 3.110e-03
: 169 : vars : 3.082e-03
: 170 : vars : 3.036e-03
: 171 : vars : 2.992e-03
: 172 : vars : 2.978e-03
: 173 : vars : 2.978e-03
: 174 : vars : 2.963e-03
: 175 : vars : 2.932e-03
: 176 : vars : 2.932e-03
: 177 : vars : 2.924e-03
: 178 : vars : 2.904e-03
: 179 : vars : 2.863e-03
: 180 : vars : 2.801e-03
: 181 : vars : 2.785e-03
: 182 : vars : 2.770e-03
: 183 : vars : 2.745e-03
: 184 : vars : 2.715e-03
: 185 : vars : 2.711e-03
: 186 : vars : 2.643e-03
: 187 : vars : 2.638e-03
: 188 : vars : 2.598e-03
: 189 : vars : 2.570e-03
: 190 : vars : 2.335e-03
: 191 : vars : 2.334e-03
: 192 : vars : 2.313e-03
: 193 : vars : 2.129e-03
: 194 : vars : 2.127e-03
: 195 : vars : 2.087e-03
: 196 : vars : 1.990e-03
: 197 : vars : 1.985e-03
: 198 : vars : 1.966e-03
: 199 : vars : 1.919e-03
: 200 : vars : 1.880e-03
: 201 : vars : 1.851e-03
: 202 : vars : 1.825e-03
: 203 : vars : 1.822e-03
: 204 : vars : 1.499e-03
: 205 : vars : 1.340e-03
: 206 : vars : 1.074e-03
: 207 : vars : 5.260e-04
: 208 : vars : 3.618e-04
: 209 : vars : 0.000e+00
: 210 : vars : 0.000e+00
: 211 : vars : 0.000e+00
: 212 : vars : 0.000e+00
: 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
: No variable ranking supplied by classifier: PyKeras
: No variable ranking supplied by classifier: PyTorch
TH1.Print Name = TrainingHistory_TMVA_DNN_CPU_trainingError, Entries= 0, Total sum= 5.14879
TH1.Print Name = TrainingHistory_TMVA_DNN_CPU_valError, Entries= 0, Total sum= 7.48335
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_trainingError, Entries= 0, Total sum= 9.07002
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_valError, Entries= 0, Total sum= 6.67854
TH1.Print Name = TrainingHistory_PyKeras_'accuracy', Entries= 0, Total sum= 6.71406
TH1.Print Name = TrainingHistory_PyKeras_'loss', Entries= 0, Total sum= 7.12067
TH1.Print Name = TrainingHistory_PyKeras_'val_accuracy', Entries= 0, Total sum= 5.1375
TH1.Print Name = TrainingHistory_PyKeras_'val_loss', Entries= 0, Total sum= 7.98333
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_PyKeras.weights.xml␛[0m
: Reading weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_PyTorch.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: 0.00722 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: 0.0192 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: 0.146 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: 0.168 sec
Factory : Test method: PyTorch for Classification performance
:
: Setup PyTorch Model for training
: Executing user initialization code from /home/sftnight/build/workspace/root-makedoc-v632/rootspi/rdoc/src/v6-32-00-patches.build/tutorials/tmva/PyTorch_Generate_CNN_Model.py
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: 0.993
[1, 8] train loss: 0.725
[1, 12] train loss: 0.700
[1] val loss: 0.699
[2, 4] train loss: 0.695
[2, 8] train loss: 0.695
[2, 12] train loss: 0.690
[2] val loss: 0.690
[3, 4] train loss: 0.687
[3, 8] train loss: 0.695
[3, 12] train loss: 0.677
[3] val loss: 0.692
[4, 4] train loss: 0.685
[4, 8] train loss: 0.685
[4, 12] train loss: 0.665
[4] val loss: 0.683
[5, 4] train loss: 0.672
[5, 8] train loss: 0.645
[5, 12] train loss: 0.645
[5] val loss: 0.656
[6, 4] train loss: 0.625
[6, 8] train loss: 0.625
[6, 12] train loss: 0.609
[6] val loss: 0.646
[7, 4] train loss: 0.558
[7, 8] train loss: 0.552
[7, 12] train loss: 0.549
[7] val loss: 0.529
[8, 4] train loss: 0.510
[8, 8] train loss: 0.515
[8, 12] train loss: 0.488
[8] val loss: 0.500
[9, 4] train loss: 0.415
[9, 8] train loss: 0.416
[9, 12] train loss: 0.492
[9] val loss: 0.548
[10, 4] train loss: 0.446
[10, 8] train loss: 0.433
[10, 12] train loss: 0.395
[10] val loss: 0.675
Finished Training on 10 Epochs!
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: 0.12 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: 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
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
:
: Evaluation results ranked by best signal efficiency and purity (area)
: -------------------------------------------------------------------------------------------------------------------
: DataSet MVA
: Name: Method: ROC-integ
: dataset PyTorch : 0.855
: dataset TMVA_CNN_CPU : 0.799
: dataset BDT : 0.765
: dataset TMVA_DNN_CPU : 0.641
: dataset PyKeras : 0.608
: -------------------------------------------------------------------------------------------------------------------
:
: 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 : 0.145 (0.260) 0.615 (0.709) 0.815 (0.898)
: dataset TMVA_CNN_CPU : 0.235 (0.125) 0.411 (0.478) 0.759 (0.812)
: dataset BDT : 0.095 (0.285) 0.365 (0.612) 0.705 (0.829)
: dataset TMVA_DNN_CPU : 0.025 (0.185) 0.190 (0.530) 0.528 (0.732)
: dataset PyKeras : 0.102 (0.097) 0.252 (0.317) 0.435 (0.538)
: -------------------------------------------------------------------------------------------------------------------
:
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