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=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 !
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)
_________________________________________________________________
(TString) "python3"[7]
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
(TString) "python3"[7]
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-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: 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: 0.853 sec
BDT : [dataset] : Evaluation of BDT on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.0176 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 | 0.90342 inf 0.182409 0.0155095 7189.96 1
: 2 | 0.685139 inf 0.18193 0.0154363 7207.48 2
: 3 | 0.621955 inf 0.181163 0.0153026 7235 3
: 4 | 0.539852 inf 0.181164 0.0153505 7237.04 4
: 5 | 0.455211 inf 0.181677 0.0153858 7216.24 5
: 6 | 0.397966 inf 0.181166 0.0153333 7236.2 6
:
: Elapsed time for training with 1600 events: 1.13 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: 0.0798 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 | 3.68125 1.7825 1.40995 0.116548 927.785 0
: 2 Minimum Test error found - save the configuration
: 2 | 1.0003 0.854546 1.41508 0.116765 924.277 0
: 3 Minimum Test error found - save the configuration
: 3 | 0.741374 0.728523 1.39969 0.114735 933.888 0
: 4 Minimum Test error found - save the configuration
: 4 | 0.690097 0.704964 1.38827 0.115107 942.536 0
: 5 | 0.681075 0.706267 1.39611 0.113221 935.389 1
: 6 Minimum Test error found - save the configuration
: 6 | 0.669654 0.698765 1.40315 0.114457 931.177 0
: 7 | 0.663951 0.704285 1.39951 0.113181 932.887 1
: 8 | 0.655312 0.713642 1.39916 0.111765 932.114 2
: 9 Minimum Test error found - save the configuration
: 9 | 0.650691 0.689436 1.41278 0.117037 926.112 0
: 10 Minimum Test error found - save the configuration
: 10 | 0.634723 0.684873 1.39922 0.114127 933.787 0
: 11 | 0.630098 0.737705 1.38708 0.112077 941.175 1
: 12 | 0.615897 0.715729 1.39494 0.115032 937.57 2
: 13 Minimum Test error found - save the configuration
: 13 | 0.592776 0.681784 1.3905 0.115062 940.857 0
: 14 Minimum Test error found - save the configuration
: 14 | 0.579896 0.67848 1.38603 0.113892 943.295 0
: 15 Minimum Test error found - save the configuration
: 15 | 0.587682 0.677731 1.38803 0.114957 942.598 0
: 16 | 0.572443 0.679296 1.39873 0.114307 934.274 1
: 17 | 0.566598 0.729071 1.39728 0.112477 933.993 2
: 18 Minimum Test error found - save the configuration
: 18 | 0.550372 0.673691 1.38406 0.114348 945.093 0
: 19 | 0.513472 0.677652 1.38483 0.112446 943.11 1
: 20 | 0.49742 0.676077 1.39673 0.11331 934.999 2
:
: Elapsed time for training with 1600 events: 28.1 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: 0.599 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 0x7f06bdec28b0>, 'predict_func': <function predict at 0x7f06bdec29d0>}
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 1/20
1/13 [=>............................] - ETA: 10s - loss: 0.8030 - accuracy: 0.5600␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
4/13 [========>.....................] - ETA: 0s - loss: 1.8623 - accuracy: 0.5200 ␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 1.4678 - accuracy: 0.4925␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
12/13 [==========================>...] - ETA: 0s - loss: 1.2324 - accuracy: 0.4867
Epoch 1: val_loss improved from inf to 0.97288, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 1s 52ms/step - loss: 1.2031 - accuracy: 0.4883 - val_loss: 0.9729 - val_accuracy: 0.5531
Epoch 2/20
1/13 [=>............................] - ETA: 0s - loss: 0.7347 - accuracy: 0.5700␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.7172 - accuracy: 0.5260␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.7045 - accuracy: 0.5367
Epoch 2: val_loss improved from 0.97288 to 0.71117, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 21ms/step - loss: 0.7037 - accuracy: 0.5258 - val_loss: 0.7112 - val_accuracy: 0.4812
Epoch 3/20
1/13 [=>............................] - ETA: 0s - loss: 0.6940 - accuracy: 0.5700␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.6823 - accuracy: 0.6100␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.6810 - accuracy: 0.6067␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.6791 - accuracy: 0.5961
Epoch 3: val_loss improved from 0.71117 to 0.68737, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 21ms/step - loss: 0.6791 - accuracy: 0.5961 - val_loss: 0.6874 - val_accuracy: 0.5531
Epoch 4/20
1/13 [=>............................] - ETA: 0s - loss: 0.6647 - accuracy: 0.6200␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.6571 - accuracy: 0.6660␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.6617 - accuracy: 0.6444␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.6678 - accuracy: 0.6250
Epoch 4: val_loss improved from 0.68737 to 0.67341, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 21ms/step - loss: 0.6678 - accuracy: 0.6250 - val_loss: 0.6734 - val_accuracy: 0.5656
Epoch 5/20
1/13 [=>............................] - ETA: 0s - loss: 0.6665 - accuracy: 0.5500␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.6543 - accuracy: 0.6320␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.6480 - accuracy: 0.6467␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.6471 - accuracy: 0.6461
Epoch 5: val_loss improved from 0.67341 to 0.67118, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 21ms/step - loss: 0.6471 - accuracy: 0.6461 - val_loss: 0.6712 - val_accuracy: 0.5750
Epoch 6/20
1/13 [=>............................] - ETA: 0s - loss: 0.6328 - accuracy: 0.6400␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.6219 - accuracy: 0.6900␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.6286 - accuracy: 0.6833␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.6301 - accuracy: 0.6789
Epoch 6: val_loss improved from 0.67118 to 0.66186, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 23ms/step - loss: 0.6301 - accuracy: 0.6789 - val_loss: 0.6619 - val_accuracy: 0.6094
Epoch 7/20
1/13 [=>............................] - ETA: 0s - loss: 0.6228 - accuracy: 0.7100␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.6071 - accuracy: 0.7200␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.6053 - accuracy: 0.7156␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.6079 - accuracy: 0.7016
Epoch 7: val_loss improved from 0.66186 to 0.65925, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 20ms/step - loss: 0.6079 - accuracy: 0.7016 - val_loss: 0.6592 - val_accuracy: 0.6500
Epoch 8/20
1/13 [=>............................] - ETA: 0s - loss: 0.6021 - accuracy: 0.6900␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.5969 - accuracy: 0.6980␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.5968 - accuracy: 0.6920
Epoch 8: val_loss did not improve from 0.65925
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 17ms/step - loss: 0.5978 - accuracy: 0.6844 - val_loss: 0.6744 - val_accuracy: 0.5688
Epoch 9/20
1/13 [=>............................] - ETA: 0s - loss: 0.5875 - accuracy: 0.6100␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
6/13 [============>.................] - ETA: 0s - loss: 0.5808 - accuracy: 0.6950␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.5795 - accuracy: 0.6920
Epoch 9: val_loss did not improve from 0.65925
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 17ms/step - loss: 0.5780 - accuracy: 0.7023 - val_loss: 0.7158 - val_accuracy: 0.5437
Epoch 10/20
1/13 [=>............................] - ETA: 0s - loss: 0.6032 - accuracy: 0.6400␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.5746 - accuracy: 0.7100␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.5612 - accuracy: 0.7322␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.5475 - accuracy: 0.7492
Epoch 10: val_loss improved from 0.65925 to 0.62834, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 1s 43ms/step - loss: 0.5475 - accuracy: 0.7492 - val_loss: 0.6283 - val_accuracy: 0.6656
Epoch 11/20
1/13 [=>............................] - ETA: 0s - loss: 0.5444 - accuracy: 0.7100␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.4999 - accuracy: 0.8020␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.5124 - accuracy: 0.7700
Epoch 11: val_loss did not improve from 0.62834
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 17ms/step - loss: 0.5089 - accuracy: 0.7727 - val_loss: 0.6378 - val_accuracy: 0.6094
Epoch 12/20
1/13 [=>............................] - ETA: 0s - loss: 0.4944 - accuracy: 0.7700␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
6/13 [============>.................] - ETA: 0s - loss: 0.5094 - accuracy: 0.7583␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
11/13 [========================>.....] - ETA: 0s - loss: 0.4992 - accuracy: 0.7700
Epoch 12: val_loss improved from 0.62834 to 0.60796, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 19ms/step - loss: 0.4961 - accuracy: 0.7758 - val_loss: 0.6080 - val_accuracy: 0.6875
Epoch 13/20
1/13 [=>............................] - ETA: 0s - loss: 0.4879 - accuracy: 0.8100␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.4510 - accuracy: 0.8320␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.4580 - accuracy: 0.8120
Epoch 13: val_loss improved from 0.60796 to 0.60526, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 20ms/step - loss: 0.4513 - accuracy: 0.8117 - val_loss: 0.6053 - val_accuracy: 0.6938
Epoch 14/20
1/13 [=>............................] - ETA: 0s - loss: 0.4217 - accuracy: 0.8700␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
6/13 [============>.................] - ETA: 0s - loss: 0.4292 - accuracy: 0.8450␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
11/13 [========================>.....] - ETA: 0s - loss: 0.4230 - accuracy: 0.8418
Epoch 14: val_loss improved from 0.60526 to 0.58697, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 20ms/step - loss: 0.4191 - accuracy: 0.8398 - val_loss: 0.5870 - val_accuracy: 0.6969
Epoch 15/20
1/13 [=>............................] - ETA: 0s - loss: 0.3349 - accuracy: 0.9100␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.3751 - accuracy: 0.8700␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
10/13 [======================>.......] - ETA: 0s - loss: 0.3765 - accuracy: 0.8740␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.3784 - accuracy: 0.8680
Epoch 15: val_loss did not improve from 0.58697
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 18ms/step - loss: 0.3784 - accuracy: 0.8680 - val_loss: 0.6386 - val_accuracy: 0.6406
Epoch 16/20
1/13 [=>............................] - ETA: 0s - loss: 0.3995 - accuracy: 0.8300␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.3697 - accuracy: 0.8580␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.3704 - accuracy: 0.8589␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.3681 - accuracy: 0.8617
Epoch 16: val_loss improved from 0.58697 to 0.56535, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 22ms/step - loss: 0.3681 - accuracy: 0.8617 - val_loss: 0.5653 - val_accuracy: 0.7219
Epoch 17/20
1/13 [=>............................] - ETA: 0s - loss: 0.3133 - accuracy: 0.9200␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
4/13 [========>.....................] - ETA: 0s - loss: 0.2975 - accuracy: 0.9300␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.3003 - accuracy: 0.9237␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
12/13 [==========================>...] - ETA: 0s - loss: 0.3109 - accuracy: 0.9067
Epoch 17: val_loss did not improve from 0.56535
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 19ms/step - loss: 0.3121 - accuracy: 0.9047 - val_loss: 0.6177 - val_accuracy: 0.6750
Epoch 18/20
1/13 [=>............................] - ETA: 0s - loss: 0.3212 - accuracy: 0.8800␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.3118 - accuracy: 0.8980␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.3483 - accuracy: 0.8578␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.3459 - accuracy: 0.8555
Epoch 18: val_loss did not improve from 0.56535
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 17ms/step - loss: 0.3459 - accuracy: 0.8555 - val_loss: 0.6725 - val_accuracy: 0.6719
Epoch 19/20
1/13 [=>............................] - ETA: 0s - loss: 0.3958 - accuracy: 0.7800␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.3344 - accuracy: 0.8480␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
9/13 [===================>..........] - ETA: 0s - loss: 0.3190 - accuracy: 0.8722␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - ETA: 0s - loss: 0.2988 - accuracy: 0.8875
Epoch 19: val_loss improved from 0.56535 to 0.56193, saving model to trained_model_cnn.h5
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 22ms/step - loss: 0.2988 - accuracy: 0.8875 - val_loss: 0.5619 - val_accuracy: 0.7500
Epoch 20/20
1/13 [=>............................] - ETA: 0s - loss: 0.2404 - accuracy: 0.9400␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
5/13 [==========>...................] - ETA: 0s - loss: 0.2292 - accuracy: 0.9440␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
8/13 [=================>............] - ETA: 0s - loss: 0.2349 - accuracy: 0.9425␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
12/13 [==========================>...] - ETA: 0s - loss: 0.2404 - accuracy: 0.9417
Epoch 20: val_loss did not improve from 0.56193
␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈␈
13/13 [==============================] - 0s 20ms/step - loss: 0.2430 - accuracy: 0.9391 - val_loss: 0.5809 - val_accuracy: 0.7219
: 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: 6.68 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: 0.263 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: 32.2 sec
PyTorch : [dataset] : Evaluation of PyTorch on training sample (1600 events)
: Elapsed time for evaluation of 1600 events: 0.419 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 : 1.016e-02
: 2 : vars : 1.008e-02
: 3 : vars : 1.002e-02
: 4 : vars : 9.772e-03
: 5 : vars : 9.560e-03
: 6 : vars : 9.473e-03
: 7 : vars : 9.117e-03
: 8 : vars : 8.872e-03
: 9 : vars : 8.817e-03
: 10 : vars : 8.726e-03
: 11 : vars : 8.581e-03
: 12 : vars : 8.362e-03
: 13 : vars : 8.245e-03
: 14 : vars : 8.200e-03
: 15 : vars : 8.134e-03
: 16 : vars : 8.086e-03
: 17 : vars : 7.984e-03
: 18 : vars : 7.961e-03
: 19 : vars : 7.916e-03
: 20 : vars : 7.892e-03
: 21 : vars : 7.857e-03
: 22 : vars : 7.773e-03
: 23 : vars : 7.704e-03
: 24 : vars : 7.540e-03
: 25 : vars : 7.499e-03
: 26 : vars : 7.479e-03
: 27 : vars : 7.440e-03
: 28 : vars : 7.341e-03
: 29 : vars : 7.259e-03
: 30 : vars : 7.235e-03
: 31 : vars : 7.231e-03
: 32 : vars : 7.198e-03
: 33 : vars : 7.102e-03
: 34 : vars : 7.082e-03
: 35 : vars : 7.025e-03
: 36 : vars : 7.005e-03
: 37 : vars : 6.936e-03
: 38 : vars : 6.887e-03
: 39 : vars : 6.865e-03
: 40 : vars : 6.838e-03
: 41 : vars : 6.770e-03
: 42 : vars : 6.738e-03
: 43 : vars : 6.617e-03
: 44 : vars : 6.606e-03
: 45 : vars : 6.601e-03
: 46 : vars : 6.521e-03
: 47 : vars : 6.444e-03
: 48 : vars : 6.441e-03
: 49 : vars : 6.438e-03
: 50 : vars : 6.392e-03
: 51 : vars : 6.384e-03
: 52 : vars : 6.374e-03
: 53 : vars : 6.370e-03
: 54 : vars : 6.370e-03
: 55 : vars : 6.350e-03
: 56 : vars : 6.337e-03
: 57 : vars : 6.322e-03
: 58 : vars : 6.314e-03
: 59 : vars : 6.307e-03
: 60 : vars : 6.288e-03
: 61 : vars : 6.254e-03
: 62 : vars : 6.169e-03
: 63 : vars : 6.154e-03
: 64 : vars : 6.073e-03
: 65 : vars : 5.904e-03
: 66 : vars : 5.881e-03
: 67 : vars : 5.861e-03
: 68 : vars : 5.817e-03
: 69 : vars : 5.717e-03
: 70 : vars : 5.692e-03
: 71 : vars : 5.691e-03
: 72 : vars : 5.671e-03
: 73 : vars : 5.659e-03
: 74 : vars : 5.650e-03
: 75 : vars : 5.605e-03
: 76 : vars : 5.556e-03
: 77 : vars : 5.449e-03
: 78 : vars : 5.447e-03
: 79 : vars : 5.447e-03
: 80 : vars : 5.429e-03
: 81 : vars : 5.418e-03
: 82 : vars : 5.396e-03
: 83 : vars : 5.391e-03
: 84 : vars : 5.345e-03
: 85 : vars : 5.276e-03
: 86 : vars : 5.261e-03
: 87 : vars : 5.260e-03
: 88 : vars : 5.260e-03
: 89 : vars : 5.249e-03
: 90 : vars : 5.161e-03
: 91 : vars : 5.157e-03
: 92 : vars : 5.149e-03
: 93 : vars : 5.120e-03
: 94 : vars : 5.053e-03
: 95 : vars : 5.042e-03
: 96 : vars : 4.992e-03
: 97 : vars : 4.947e-03
: 98 : vars : 4.895e-03
: 99 : vars : 4.876e-03
: 100 : vars : 4.753e-03
: 101 : vars : 4.708e-03
: 102 : vars : 4.681e-03
: 103 : vars : 4.670e-03
: 104 : vars : 4.665e-03
: 105 : vars : 4.629e-03
: 106 : vars : 4.625e-03
: 107 : vars : 4.585e-03
: 108 : vars : 4.529e-03
: 109 : vars : 4.516e-03
: 110 : vars : 4.490e-03
: 111 : vars : 4.487e-03
: 112 : vars : 4.469e-03
: 113 : vars : 4.457e-03
: 114 : vars : 4.456e-03
: 115 : vars : 4.336e-03
: 116 : vars : 4.278e-03
: 117 : vars : 4.238e-03
: 118 : vars : 4.216e-03
: 119 : vars : 4.112e-03
: 120 : vars : 4.081e-03
: 121 : vars : 4.050e-03
: 122 : vars : 4.027e-03
: 123 : vars : 3.996e-03
: 124 : vars : 3.984e-03
: 125 : vars : 3.978e-03
: 126 : vars : 3.968e-03
: 127 : vars : 3.867e-03
: 128 : vars : 3.862e-03
: 129 : vars : 3.824e-03
: 130 : vars : 3.749e-03
: 131 : vars : 3.719e-03
: 132 : vars : 3.670e-03
: 133 : vars : 3.668e-03
: 134 : vars : 3.661e-03
: 135 : vars : 3.652e-03
: 136 : vars : 3.627e-03
: 137 : vars : 3.540e-03
: 138 : vars : 3.533e-03
: 139 : vars : 3.483e-03
: 140 : vars : 3.481e-03
: 141 : vars : 3.469e-03
: 142 : vars : 3.457e-03
: 143 : vars : 3.443e-03
: 144 : vars : 3.410e-03
: 145 : vars : 3.394e-03
: 146 : vars : 3.384e-03
: 147 : vars : 3.369e-03
: 148 : vars : 3.332e-03
: 149 : vars : 3.290e-03
: 150 : vars : 3.279e-03
: 151 : vars : 3.184e-03
: 152 : vars : 3.179e-03
: 153 : vars : 3.157e-03
: 154 : vars : 3.144e-03
: 155 : vars : 3.120e-03
: 156 : vars : 3.099e-03
: 157 : vars : 3.077e-03
: 158 : vars : 3.039e-03
: 159 : vars : 3.032e-03
: 160 : vars : 3.029e-03
: 161 : vars : 2.950e-03
: 162 : vars : 2.945e-03
: 163 : vars : 2.924e-03
: 164 : vars : 2.922e-03
: 165 : vars : 2.903e-03
: 166 : vars : 2.851e-03
: 167 : vars : 2.832e-03
: 168 : vars : 2.828e-03
: 169 : vars : 2.823e-03
: 170 : vars : 2.768e-03
: 171 : vars : 2.695e-03
: 172 : vars : 2.686e-03
: 173 : vars : 2.599e-03
: 174 : vars : 2.599e-03
: 175 : vars : 2.584e-03
: 176 : vars : 2.537e-03
: 177 : vars : 2.535e-03
: 178 : vars : 2.512e-03
: 179 : vars : 2.497e-03
: 180 : vars : 2.497e-03
: 181 : vars : 2.476e-03
: 182 : vars : 2.435e-03
: 183 : vars : 2.427e-03
: 184 : vars : 2.360e-03
: 185 : vars : 2.329e-03
: 186 : vars : 2.297e-03
: 187 : vars : 2.228e-03
: 188 : vars : 2.195e-03
: 189 : vars : 2.154e-03
: 190 : vars : 2.147e-03
: 191 : vars : 2.108e-03
: 192 : vars : 2.072e-03
: 193 : vars : 2.008e-03
: 194 : vars : 1.987e-03
: 195 : vars : 1.806e-03
: 196 : vars : 1.801e-03
: 197 : vars : 1.800e-03
: 198 : vars : 1.701e-03
: 199 : vars : 1.688e-03
: 200 : vars : 1.591e-03
: 201 : vars : 1.491e-03
: 202 : vars : 1.484e-03
: 203 : vars : 7.278e-04
: 204 : vars : 6.415e-04
: 205 : vars : 5.758e-04
: 206 : vars : 5.448e-04
: 207 : vars : 4.241e-04
: 208 : vars : 1.853e-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= 3.60354
TH1.Print Name = TrainingHistory_TMVA_DNN_CPU_valError, Entries= 0, Total sum= inf
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_trainingError, Entries= 0, Total sum= 15.7751
TH1.Print Name = TrainingHistory_TMVA_CNN_CPU_valError, Entries= 0, Total sum= 15.195
TH1.Print Name = TrainingHistory_PyKeras_'accuracy', Entries= 0, Total sum= 14.9141
TH1.Print Name = TrainingHistory_PyKeras_'loss', Entries= 0, Total sum= 10.6834
TH1.Print Name = TrainingHistory_PyKeras_'val_accuracy', Entries= 0, Total sum= 12.6344
TH1.Print Name = TrainingHistory_PyKeras_'val_loss', Entries= 0, Total sum= 13.1306
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: 0.00577 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: 0.15 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: 0.187 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
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: 1.147
[1, 8] train loss: 0.737
[1, 12] train loss: 0.714
[1] val loss: 0.691
[2, 4] train loss: 0.697
[2, 8] train loss: 0.701
[2, 12] train loss: 0.689
[2] val loss: 0.688
[3, 4] train loss: 0.681
[3, 8] train loss: 0.691
[3, 12] train loss: 0.682
[3] val loss: 0.686
[4, 4] train loss: 0.665
[4, 8] train loss: 0.676
[4, 12] train loss: 0.656
[4] val loss: 0.669
[5, 4] train loss: 0.630
[5, 8] train loss: 0.639
[5, 12] train loss: 0.619
[5] val loss: 0.744
[6, 4] train loss: 0.600
[6, 8] train loss: 0.533
[6, 12] train loss: 0.584
[6] val loss: 0.849
[7, 4] train loss: 0.560
[7, 8] train loss: 0.451
[7, 12] train loss: 0.478
[7] val loss: 0.544
[8, 4] train loss: 0.438
[8, 8] train loss: 0.361
[8, 12] train loss: 0.395
[8] val loss: 0.686
[9, 4] train loss: 0.435
[9, 8] train loss: 0.372
[9, 12] train loss: 0.330
[9] val loss: 0.605
[10, 4] train loss: 0.308
[10, 8] train loss: 0.294
[10, 12] train loss: 0.302
[10] val loss: 0.736
[11, 4] train loss: 0.331
[11, 8] train loss: 0.343
[11, 12] train loss: 0.362
[11] val loss: 1.125
[12, 4] train loss: 0.568
[12, 8] train loss: 0.438
[12, 12] train loss: 0.339
[12] val loss: 0.824
[13, 4] train loss: 0.351
[13, 8] train loss: 0.292
[13, 12] train loss: 0.276
[13] val loss: 0.586
[14, 4] train loss: 0.324
[14, 8] train loss: 0.312
[14, 12] train loss: 0.284
[14] val loss: 0.900
[15, 4] train loss: 0.355
[15, 8] train loss: 0.274
[15, 12] train loss: 0.287
[15] val loss: 0.859
[16, 4] train loss: 0.371
[16, 8] train loss: 0.321
[16, 12] train loss: 0.432
[16] val loss: 0.862
[17, 4] train loss: 0.411
[17, 8] train loss: 0.548
[17, 12] train loss: 0.369
[17] val loss: 0.954
[18, 4] train loss: 0.395
[18, 8] train loss: 0.333
[18, 12] train loss: 0.283
[18] val loss: 0.638
[19, 4] train loss: 0.288
[19, 8] train loss: 0.300
[19, 12] train loss: 0.209
[19] val loss: 0.711
[20, 4] train loss: 0.201
[20, 8] train loss: 0.200
[20, 12] train loss: 0.165
[20] val loss: 0.652
Finished Training on 20 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: 0.121 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...
:
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.005, fb=-0.005), refValue = 0.005
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.015, fb=-0.015), refValue = 0.015
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.025, fb=-0.025), refValue = 0.025
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.035, fb=-0.035), refValue = 0.035
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.045, fb=-0.045), refValue = 0.045
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.055, fb=-0.055), refValue = 0.055
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.065, fb=-0.065), refValue = 0.065
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.075, fb=-0.075), refValue = 0.075
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.085, fb=-0.085), refValue = 0.085
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.095, fb=-0.095), refValue = 0.095
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.105, fb=-0.105), refValue = 0.105
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.115, fb=-0.115), refValue = 0.115
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.125, fb=-0.125), refValue = 0.125
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.135, fb=-0.135), refValue = 0.135
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.145, fb=-0.145), refValue = 0.145
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.155, fb=-0.155), refValue = 0.155
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.165, fb=-0.165), refValue = 0.165
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.175, fb=-0.175), refValue = 0.175
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.185, fb=-0.185), refValue = 0.185
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.195, fb=-0.195), refValue = 0.195
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.205, fb=-0.205), refValue = 0.205
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.215, fb=-0.215), refValue = 0.215
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.225, fb=-0.225), refValue = 0.225
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.235, fb=-0.235), refValue = 0.235
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.245, fb=-0.245), refValue = 0.245
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.255, fb=-0.255), refValue = 0.255
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.265, fb=-0.265), refValue = 0.265
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.275, fb=-0.275), refValue = 0.275
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.285, fb=-0.285), refValue = 0.285
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.295, fb=-0.295), refValue = 0.295
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.305, fb=-0.305), refValue = 0.305
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.315, fb=-0.315), refValue = 0.315
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.325, fb=-0.325), refValue = 0.325
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.335, fb=-0.335), refValue = 0.335
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.345, fb=-0.345), refValue = 0.345
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.355, fb=-0.355), refValue = 0.355
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.365, fb=-0.365), refValue = 0.365
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.375, fb=-0.375), refValue = 0.375
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.385, fb=-0.385), refValue = 0.385
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.395, fb=-0.395), refValue = 0.395
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.405, fb=-0.405), refValue = 0.405
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.415, fb=-0.415), refValue = 0.415
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.425, fb=-0.425), refValue = 0.425
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.435, fb=-0.435), refValue = 0.435
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.445, fb=-0.445), refValue = 0.445
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.455, fb=-0.455), refValue = 0.455
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.465, fb=-0.465), refValue = 0.465
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.475, fb=-0.475), refValue = 0.475
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.485, fb=-0.485), refValue = 0.485
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.495, fb=-0.495), refValue = 0.495
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.505, fb=-0.505), refValue = 0.505
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.515, fb=-0.515), refValue = 0.515
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.525, fb=-0.525), refValue = 0.525
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.535, fb=-0.535), refValue = 0.535
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.545, fb=-0.545), refValue = 0.545
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.555, fb=-0.555), refValue = 0.555
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.565, fb=-0.565), refValue = 0.565
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.575, fb=-0.575), refValue = 0.575
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.585, fb=-0.585), refValue = 0.585
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.595, fb=-0.595), refValue = 0.595
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.605, fb=-0.605), refValue = 0.605
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.615, fb=-0.615), refValue = 0.615
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.625, fb=-0.625), refValue = 0.625
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.635, fb=-0.635), refValue = 0.635
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.645, fb=-0.645), refValue = 0.645
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.655, fb=-0.655), refValue = 0.655
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.665, fb=-0.665), refValue = 0.665
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.675, fb=-0.675), refValue = 0.675
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.685, fb=-0.685), refValue = 0.685
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.695, fb=-0.695), refValue = 0.695
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.705, fb=-0.705), refValue = 0.705
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.715, fb=-0.715), refValue = 0.715
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.725, fb=-0.725), refValue = 0.725
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.735, fb=-0.735), refValue = 0.735
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.745, fb=-0.745), refValue = 0.745
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.755, fb=-0.755), refValue = 0.755
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.765, fb=-0.765), refValue = 0.765
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.775, fb=-0.775), refValue = 0.775
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.785, fb=-0.785), refValue = 0.785
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.795, fb=-0.795), refValue = 0.795
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.805, fb=-0.805), refValue = 0.805
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.815, fb=-0.815), refValue = 0.815
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.825, fb=-0.825), refValue = 0.825
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.835, fb=-0.835), refValue = 0.835
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.845, fb=-0.845), refValue = 0.845
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.855, fb=-0.855), refValue = 0.855
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.865, fb=-0.865), refValue = 0.865
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.875, fb=-0.875), refValue = 0.875
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.885, fb=-0.885), refValue = 0.885
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.895, fb=-0.895), refValue = 0.895
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.905, fb=-0.905), refValue = 0.905
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.915, fb=-0.915), refValue = 0.915
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.925, fb=-0.925), refValue = 0.925
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.935, fb=-0.935), refValue = 0.935
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.945, fb=-0.945), refValue = 0.945
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.955, fb=-0.955), refValue = 0.955
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.965, fb=-0.965), refValue = 0.965
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.975, fb=-0.975), refValue = 0.975
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.985, fb=-0.985), refValue = 0.985
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.995, fb=-0.995), refValue = 0.995
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.9999, fb=-0.9999), refValue = 0.9999
: Evaluate deep neural network on CPU using batches with size = 1000
:
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.005, fb=-0.005), refValue = 0.005
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.015, fb=-0.015), refValue = 0.015
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.025, fb=-0.025), refValue = 0.025
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.035, fb=-0.035), refValue = 0.035
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.045, fb=-0.045), refValue = 0.045
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.055, fb=-0.055), refValue = 0.055
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.065, fb=-0.065), refValue = 0.065
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.075, fb=-0.075), refValue = 0.075
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.085, fb=-0.085), refValue = 0.085
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.095, fb=-0.095), refValue = 0.095
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.105, fb=-0.105), refValue = 0.105
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.115, fb=-0.115), refValue = 0.115
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.125, fb=-0.125), refValue = 0.125
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.135, fb=-0.135), refValue = 0.135
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.145, fb=-0.145), refValue = 0.145
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.155, fb=-0.155), refValue = 0.155
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.165, fb=-0.165), refValue = 0.165
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.175, fb=-0.175), refValue = 0.175
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.185, fb=-0.185), refValue = 0.185
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.195, fb=-0.195), refValue = 0.195
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.205, fb=-0.205), refValue = 0.205
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.215, fb=-0.215), refValue = 0.215
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.225, fb=-0.225), refValue = 0.225
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.235, fb=-0.235), refValue = 0.235
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.245, fb=-0.245), refValue = 0.245
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.255, fb=-0.255), refValue = 0.255
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.265, fb=-0.265), refValue = 0.265
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.275, fb=-0.275), refValue = 0.275
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.285, fb=-0.285), refValue = 0.285
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.295, fb=-0.295), refValue = 0.295
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.305, fb=-0.305), refValue = 0.305
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.315, fb=-0.315), refValue = 0.315
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.325, fb=-0.325), refValue = 0.325
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.335, fb=-0.335), refValue = 0.335
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.345, fb=-0.345), refValue = 0.345
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.355, fb=-0.355), refValue = 0.355
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.365, fb=-0.365), refValue = 0.365
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.375, fb=-0.375), refValue = 0.375
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.385, fb=-0.385), refValue = 0.385
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.395, fb=-0.395), refValue = 0.395
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.405, fb=-0.405), refValue = 0.405
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.415, fb=-0.415), refValue = 0.415
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.425, fb=-0.425), refValue = 0.425
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.435, fb=-0.435), refValue = 0.435
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.445, fb=-0.445), refValue = 0.445
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.455, fb=-0.455), refValue = 0.455
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.465, fb=-0.465), refValue = 0.465
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.475, fb=-0.475), refValue = 0.475
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.485, fb=-0.485), refValue = 0.485
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.495, fb=-0.495), refValue = 0.495
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.505, fb=-0.505), refValue = 0.505
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.515, fb=-0.515), refValue = 0.515
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.525, fb=-0.525), refValue = 0.525
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.535, fb=-0.535), refValue = 0.535
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.545, fb=-0.545), refValue = 0.545
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.555, fb=-0.555), refValue = 0.555
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.565, fb=-0.565), refValue = 0.565
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.575, fb=-0.575), refValue = 0.575
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.585, fb=-0.585), refValue = 0.585
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.595, fb=-0.595), refValue = 0.595
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.605, fb=-0.605), refValue = 0.605
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.615, fb=-0.615), refValue = 0.615
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.625, fb=-0.625), refValue = 0.625
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.635, fb=-0.635), refValue = 0.635
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.645, fb=-0.645), refValue = 0.645
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.655, fb=-0.655), refValue = 0.655
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.665, fb=-0.665), refValue = 0.665
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.675, fb=-0.675), refValue = 0.675
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.685, fb=-0.685), refValue = 0.685
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.695, fb=-0.695), refValue = 0.695
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.705, fb=-0.705), refValue = 0.705
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.715, fb=-0.715), refValue = 0.715
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.725, fb=-0.725), refValue = 0.725
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.735, fb=-0.735), refValue = 0.735
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.745, fb=-0.745), refValue = 0.745
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.755, fb=-0.755), refValue = 0.755
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.765, fb=-0.765), refValue = 0.765
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.775, fb=-0.775), refValue = 0.775
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.785, fb=-0.785), refValue = 0.785
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.795, fb=-0.795), refValue = 0.795
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.805, fb=-0.805), refValue = 0.805
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.815, fb=-0.815), refValue = 0.815
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.825, fb=-0.825), refValue = 0.825
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.835, fb=-0.835), refValue = 0.835
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.845, fb=-0.845), refValue = 0.845
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.855, fb=-0.855), refValue = 0.855
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.865, fb=-0.865), refValue = 0.865
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.875, fb=-0.875), refValue = 0.875
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.885, fb=-0.885), refValue = 0.885
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.895, fb=-0.895), refValue = 0.895
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.905, fb=-0.905), refValue = 0.905
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.915, fb=-0.915), refValue = 0.915
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.925, fb=-0.925), refValue = 0.925
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.935, fb=-0.935), refValue = 0.935
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.945, fb=-0.945), refValue = 0.945
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.955, fb=-0.955), refValue = 0.955
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.965, fb=-0.965), refValue = 0.965
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.975, fb=-0.975), refValue = 0.975
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.985, fb=-0.985), refValue = 0.985
<WARNING> : <Root> initial interval w/o root: (a=0.5, b=0.5), (Eff_a=0, Eff_b=0), (fa=-0.995, fb=-0.995), refValue = 0.995
: 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 : 0.767
: dataset PyKeras : 0.722
: dataset BDT : 0.692
: dataset TMVA_CNN_CPU : 0.642
: dataset TMVA_DNN_CPU : 0.530
: -------------------------------------------------------------------------------------------------------------------
:
: 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 (0.238) 0.335 (0.625) 0.740 (0.839)
: dataset PyKeras : 0.085 (0.250) 0.285 (0.608) 0.605 (0.852)
: dataset BDT : 0.035 (0.186) 0.315 (0.508) 0.575 (0.759)
: dataset TMVA_CNN_CPU : 0.015 (0.092) 0.225 (0.333) 0.445 (0.655)
: dataset TMVA_DNN_CPU : 0.000 (0.000) 0.000 (0.000) 0.000 (0.000)
: -------------------------------------------------------------------------------------------------------------------
:
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
