ClassificationKeras launching

Newbie
18

Thank you very much for the help Lorenzo, with Tensorflow 2.4, and Keras 2.3, adding the tf.keras=True attribute makes the 6.24 tutorial work.

I’ll work on uploading this to the snap store now so John can get on with using it.

#!/usr/bin/env python
## \file
## \ingroup tutorial_tmva_keras
## \notebook -nodraw
## This tutorial shows how to do classification in TMVA with neural networks
## trained with keras.
##
## \macro_code
##
## \date 2017
## \author TMVA Team

from ROOT import TMVA, TFile, TTree, TCut
from subprocess import call
from os.path import isfile

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.optimizers import SGD

# Setup TMVA
TMVA.Tools.Instance()
TMVA.PyMethodBase.PyInitialize()

output = TFile.Open('TMVA.root', 'RECREATE')
factory = TMVA.Factory('TMVAClassification', output,
                       '!V:!Silent:Color:DrawProgressBar:Transformations=D,G:AnalysisType=Classification')

# Load data
if not isfile('tmva_class_example.root'):
    call(['curl', '-O', 'https://root.cern.ch/files/tmva_class_example.root'])

data = TFile.Open('tmva_class_example.root')
signal = data.Get('TreeS')
background = data.Get('TreeB')

dataloader = TMVA.DataLoader('dataset')
for branch in signal.GetListOfBranches():
    dataloader.AddVariable(branch.GetName())

dataloader.AddSignalTree(signal, 1.0)
dataloader.AddBackgroundTree(background, 1.0)
dataloader.PrepareTrainingAndTestTree(TCut(''),
                                      'nTrain_Signal=4000:nTrain_Background=4000:SplitMode=Random:NormMode=NumEvents:!V')

# Generate model

# Define model
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=4))
model.add(Dense(2, activation='softmax'))

# Set loss and optimizer
model.compile(loss='categorical_crossentropy',
              optimizer=SGD(lr=0.01), metrics=['accuracy', ])

# Store model to file
model.save('model.h5')
model.summary()

# Book methods
factory.BookMethod(dataloader, TMVA.Types.kFisher, 'Fisher',
                   '!H:!V:Fisher:VarTransform=D,G')
factory.BookMethod(dataloader, TMVA.Types.kPyKeras, 'PyKeras',
                   'H:!V:VarTransform=D,G:FilenameModel=model.h5:NumEpochs=20:BatchSize=32:tf.keras=True')

# Run training, test and evaluation
factory.TrainAllMethods()
factory.TestAllMethods()
factory.EvaluateAllMethods()

Edit: it’s live now, run sudo snap refresh and hopefully revision 125 will work absolutely fine with the snippet above

2 Likes