TMVA_CNN_Classification.py File Reference

Detailed Description

TMVA Classification Example Using a Convolutional Neural Network

This is an example of using a CNN in TMVA. We do classification using a toy image data set that is generated when running the example macro

Running with nthreads  = 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                  : ␛[1mTrain all methods␛[0m
Factory                  : Train method: BDT for Classification
                         : 
BDT                      : #events: (reweighted) sig: 800 bkg: 800
                         : #events: (unweighted) sig: 800 bkg: 800
                         : Training 400 Decision Trees ... patience please
                         : Elapsed time for training with 1600 events: 1.3 sec         
BDT                      : [dataset] : Evaluation of BDT on training sample (1600 events)
                         : Elapsed time for evaluation of 1600 events: 0.0138 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
                         : 
                         : Ranking input variables (method specific)...
BDT                      : Ranking result (top variable is best ranked)
                         : --------------------------------------
                         : Rank : Variable  : Variable Importance
                         : --------------------------------------
                         :    1 : vars      : 1.065e-02
                         :    2 : vars      : 9.549e-03
                         :    3 : vars      : 8.529e-03
                         :    4 : vars      : 8.310e-03
                         :    5 : vars      : 8.242e-03
                         :    6 : vars      : 7.781e-03
                         :    7 : vars      : 7.640e-03
                         :    8 : vars      : 7.627e-03
                         :    9 : vars      : 7.552e-03
                         :   10 : vars      : 7.330e-03
                         :   11 : vars      : 7.252e-03
                         :   12 : vars      : 7.243e-03
                         :   13 : vars      : 7.225e-03
                         :   14 : vars      : 7.163e-03
                         :   15 : vars      : 7.103e-03
                         :   16 : vars      : 7.091e-03
                         :   17 : vars      : 7.010e-03
                         :   18 : vars      : 6.955e-03
                         :   19 : vars      : 6.946e-03
                         :   20 : vars      : 6.935e-03
                         :   21 : vars      : 6.925e-03
                         :   22 : vars      : 6.899e-03
                         :   23 : vars      : 6.797e-03
                         :   24 : vars      : 6.764e-03
                         :   25 : vars      : 6.749e-03
                         :   26 : vars      : 6.708e-03
                         :   27 : vars      : 6.686e-03
                         :   28 : vars      : 6.580e-03
                         :   29 : vars      : 6.552e-03
                         :   30 : vars      : 6.339e-03
                         :   31 : vars      : 6.311e-03
                         :   32 : vars      : 6.299e-03
                         :   33 : vars      : 6.144e-03
                         :   34 : vars      : 6.123e-03
                         :   35 : vars      : 6.089e-03
                         :   36 : vars      : 6.048e-03
                         :   37 : vars      : 6.028e-03
                         :   38 : vars      : 5.985e-03
                         :   39 : vars      : 5.929e-03
                         :   40 : vars      : 5.926e-03
                         :   41 : vars      : 5.916e-03
                         :   42 : vars      : 5.899e-03
                         :   43 : vars      : 5.896e-03
                         :   44 : vars      : 5.802e-03
                         :   45 : vars      : 5.772e-03
                         :   46 : vars      : 5.753e-03
                         :   47 : vars      : 5.746e-03
                         :   48 : vars      : 5.672e-03
                         :   49 : vars      : 5.592e-03
                         :   50 : vars      : 5.577e-03
                         :   51 : vars      : 5.543e-03
                         :   52 : vars      : 5.486e-03
                         :   53 : vars      : 5.481e-03
                         :   54 : vars      : 5.454e-03
                         :   55 : vars      : 5.452e-03
                         :   56 : vars      : 5.412e-03
                         :   57 : vars      : 5.362e-03
                         :   58 : vars      : 5.303e-03
                         :   59 : vars      : 5.284e-03
                         :   60 : vars      : 5.249e-03
                         :   61 : vars      : 5.246e-03
                         :   62 : vars      : 5.202e-03
                         :   63 : vars      : 5.201e-03
                         :   64 : vars      : 5.191e-03
                         :   65 : vars      : 5.186e-03
                         :   66 : vars      : 5.180e-03
                         :   67 : vars      : 5.176e-03
                         :   68 : vars      : 5.154e-03
                         :   69 : vars      : 5.092e-03
                         :   70 : vars      : 5.089e-03
                         :   71 : vars      : 5.087e-03
                         :   72 : vars      : 5.086e-03
                         :   73 : vars      : 5.044e-03
                         :   74 : vars      : 4.987e-03
                         :   75 : vars      : 4.841e-03
                         :   76 : vars      : 4.808e-03
                         :   77 : vars      : 4.778e-03
                         :   78 : vars      : 4.742e-03
                         :   79 : vars      : 4.731e-03
                         :   80 : vars      : 4.697e-03
                         :   81 : vars      : 4.671e-03
                         :   82 : vars      : 4.667e-03
                         :   83 : vars      : 4.637e-03
                         :   84 : vars      : 4.624e-03
                         :   85 : vars      : 4.621e-03
                         :   86 : vars      : 4.621e-03
                         :   87 : vars      : 4.535e-03
                         :   88 : vars      : 4.518e-03
                         :   89 : vars      : 4.449e-03
                         :   90 : vars      : 4.444e-03
                         :   91 : vars      : 4.437e-03
                         :   92 : vars      : 4.392e-03
                         :   93 : vars      : 4.378e-03
                         :   94 : vars      : 4.353e-03
                         :   95 : vars      : 4.327e-03
                         :   96 : vars      : 4.324e-03
                         :   97 : vars      : 4.300e-03
                         :   98 : vars      : 4.294e-03
                         :   99 : vars      : 4.261e-03
                         :  100 : vars      : 4.253e-03
                         :  101 : vars      : 4.227e-03
                         :  102 : vars      : 4.197e-03
                         :  103 : vars      : 4.170e-03
                         :  104 : vars      : 4.134e-03
                         :  105 : vars      : 4.109e-03
                         :  106 : vars      : 4.083e-03
                         :  107 : vars      : 4.059e-03
                         :  108 : vars      : 4.055e-03
                         :  109 : vars      : 4.017e-03
                         :  110 : vars      : 4.014e-03
                         :  111 : vars      : 4.013e-03
                         :  112 : vars      : 4.009e-03
                         :  113 : vars      : 4.006e-03
                         :  114 : vars      : 3.996e-03
                         :  115 : vars      : 3.980e-03
                         :  116 : vars      : 3.941e-03
                         :  117 : vars      : 3.913e-03
                         :  118 : vars      : 3.884e-03
                         :  119 : vars      : 3.882e-03
                         :  120 : vars      : 3.879e-03
                         :  121 : vars      : 3.869e-03
                         :  122 : vars      : 3.868e-03
                         :  123 : vars      : 3.863e-03
                         :  124 : vars      : 3.862e-03
                         :  125 : vars      : 3.854e-03
                         :  126 : vars      : 3.852e-03
                         :  127 : vars      : 3.837e-03
                         :  128 : vars      : 3.824e-03
                         :  129 : vars      : 3.752e-03
                         :  130 : vars      : 3.720e-03
                         :  131 : vars      : 3.700e-03
                         :  132 : vars      : 3.689e-03
                         :  133 : vars      : 3.687e-03
                         :  134 : vars      : 3.682e-03
                         :  135 : vars      : 3.665e-03
                         :  136 : vars      : 3.645e-03
                         :  137 : vars      : 3.637e-03
                         :  138 : vars      : 3.629e-03
                         :  139 : vars      : 3.622e-03
                         :  140 : vars      : 3.615e-03
                         :  141 : vars      : 3.594e-03
                         :  142 : vars      : 3.570e-03
                         :  143 : vars      : 3.549e-03
                         :  144 : vars      : 3.536e-03
                         :  145 : vars      : 3.522e-03
                         :  146 : vars      : 3.521e-03
                         :  147 : vars      : 3.493e-03
                         :  148 : vars      : 3.488e-03
                         :  149 : vars      : 3.475e-03
                         :  150 : vars      : 3.444e-03
                         :  151 : vars      : 3.428e-03
                         :  152 : vars      : 3.428e-03
                         :  153 : vars      : 3.426e-03
                         :  154 : vars      : 3.408e-03
                         :  155 : vars      : 3.392e-03
                         :  156 : vars      : 3.380e-03
                         :  157 : vars      : 3.377e-03
                         :  158 : vars      : 3.331e-03
                         :  159 : vars      : 3.310e-03
                         :  160 : vars      : 3.310e-03
                         :  161 : vars      : 3.302e-03
                         :  162 : vars      : 3.298e-03
                         :  163 : vars      : 3.288e-03
                         :  164 : vars      : 3.258e-03
                         :  165 : vars      : 3.249e-03
                         :  166 : vars      : 3.233e-03
                         :  167 : vars      : 3.195e-03
                         :  168 : vars      : 3.162e-03
                         :  169 : vars      : 3.147e-03
                         :  170 : vars      : 3.090e-03
                         :  171 : vars      : 3.073e-03
                         :  172 : vars      : 3.055e-03
                         :  173 : vars      : 3.012e-03
                         :  174 : vars      : 3.012e-03
                         :  175 : vars      : 3.003e-03
                         :  176 : vars      : 3.002e-03
                         :  177 : vars      : 2.999e-03
                         :  178 : vars      : 2.997e-03
                         :  179 : vars      : 2.995e-03
                         :  180 : vars      : 2.974e-03
                         :  181 : vars      : 2.925e-03
                         :  182 : vars      : 2.897e-03
                         :  183 : vars      : 2.896e-03
                         :  184 : vars      : 2.888e-03
                         :  185 : vars      : 2.878e-03
                         :  186 : vars      : 2.859e-03
                         :  187 : vars      : 2.822e-03
                         :  188 : vars      : 2.812e-03
                         :  189 : vars      : 2.801e-03
                         :  190 : vars      : 2.799e-03
                         :  191 : vars      : 2.770e-03
                         :  192 : vars      : 2.716e-03
                         :  193 : vars      : 2.701e-03
                         :  194 : vars      : 2.660e-03
                         :  195 : vars      : 2.651e-03
                         :  196 : vars      : 2.648e-03
                         :  197 : vars      : 2.637e-03
                         :  198 : vars      : 2.593e-03
                         :  199 : vars      : 2.589e-03
                         :  200 : vars      : 2.581e-03
                         :  201 : vars      : 2.546e-03
                         :  202 : vars      : 2.542e-03
                         :  203 : vars      : 2.468e-03
                         :  204 : vars      : 2.459e-03
                         :  205 : vars      : 2.457e-03
                         :  206 : vars      : 2.446e-03
                         :  207 : vars      : 2.439e-03
                         :  208 : vars      : 2.435e-03
                         :  209 : vars      : 2.421e-03
                         :  210 : vars      : 2.412e-03
                         :  211 : vars      : 2.394e-03
                         :  212 : vars      : 2.306e-03
                         :  213 : vars      : 2.296e-03
                         :  214 : vars      : 2.296e-03
                         :  215 : vars      : 2.264e-03
                         :  216 : vars      : 2.243e-03
                         :  217 : vars      : 2.238e-03
                         :  218 : vars      : 2.174e-03
                         :  219 : vars      : 2.166e-03
                         :  220 : vars      : 2.136e-03
                         :  221 : vars      : 2.084e-03
                         :  222 : vars      : 2.041e-03
                         :  223 : vars      : 1.999e-03
                         :  224 : vars      : 1.989e-03
                         :  225 : vars      : 1.974e-03
                         :  226 : vars      : 1.900e-03
                         :  227 : vars      : 1.746e-03
                         :  228 : vars      : 1.676e-03
                         :  229 : vars      : 1.600e-03
                         :  230 : vars      : 1.526e-03
                         :  231 : vars      : 1.400e-03
                         :  232 : vars      : 1.360e-03
                         :  233 : vars      : 1.319e-03
                         :  234 : vars      : 1.293e-03
                         :  235 : vars      : 1.203e-03
                         :  236 : vars      : 1.185e-03
                         :  237 : vars      : 6.177e-04
                         :  238 : vars      : 4.318e-04
                         :  239 : vars      : 3.337e-04
                         :  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
                         : --------------------------------------
Factory                  : === Destroy and recreate all methods via weight files for testing ===
                         : 
                         : Reading weight file: ␛[0;36mdataset/weights/TMVA_CNN_Classification_BDT.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: 0.00346 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
                         : 
                         : Evaluation results ranked by best signal efficiency and purity (area)
                         : -------------------------------------------------------------------------------------------------------------------
                         : DataSet       MVA                       
                         : Name:         Method:          ROC-integ
                         : dataset       BDT            : 0.773
                         : -------------------------------------------------------------------------------------------------------------------
                         : 
                         : 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              BDT            : 0.070 (0.308)       0.375 (0.706)      0.703 (0.879)
                         : -------------------------------------------------------------------------------------------------------------------
                         : 
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

 
 
# TMVA Classification Example Using a Convolutional Neural Network
 
 
## Helper function to create input images data
## we create a signal and background 2D histograms from 2d gaussians
## with a location (means in X and Y)  different for each event
## The difference between signal and background is in the gaussian width.
## The width for the background gaussian is slightly larger than the signal width by few % values
 
import ROOT
 
import os
import importlib.util
 
opt = [1, 1, 1, 1, 1]
useTMVACNN = opt[0] if len(opt) > 0  else False
useKerasCNN = opt[1] if len(opt) > 1 else False
useTMVADNN = opt[2] if len(opt) > 2 else False
useTMVABDT = opt[3] if len(opt) > 3 else False
usePyTorchCNN = opt[4] if len(opt) > 4 else False
 
TMVA = ROOT.TMVA
TFile = ROOT.TFile
 
TMVA.Tools.Instance()
 
def MakeImagesTree(n, nh, nw):
    # image size (nh x nw)
    ntot = nh * nw
    fileOutName = "images_data_16x16.root"
    nRndmEvts = 10000  # number of events we use to fill each image
    delta_sigma = 0.1  # 5% difference in the sigma
    pixelNoise = 5
 
    sX1 = 3
    sY1 = 3
    sX2 = sX1 + delta_sigma
    sY2 = sY1 - delta_sigma
    h1 = ROOT.TH2D("h1", "h1", nh, 0, 10, nw, 0, 10)
    h2 = ROOT.TH2D("h2", "h2", nh, 0, 10, nw, 0, 10)
    f1 = ROOT.TF2("f1", "xygaus")
    f2 = ROOT.TF2("f2", "xygaus")
    sgn = ROOT.TTree("sig_tree", "signal_tree")
    bkg = ROOT.TTree("bkg_tree", "background_tree")
 
    f = TFile(fileOutName, "RECREATE")
    x1 = ROOT.std.vector["float"](ntot)
    x2 = ROOT.std.vector["float"](ntot)
 
    # create signal and background trees with a single branch
    # an std::vector<float> of size nh x nw containing the image data
    bkg.Branch("vars", "std::vector<float>", x1)
    sgn.Branch("vars", "std::vector<float>", x2)
 
    sgn.SetDirectory(f)
    bkg.SetDirectory(f)
 
    f1.SetParameters(1, 5, sX1, 5, sY1)
    f2.SetParameters(1, 5, sX2, 5, sY2)
    ROOT.gRandom.SetSeed(0)
    ROOT.Info("TMVA_CNN_Classification", "Filling ROOT tree \n")
    for i in range(n):
        if i % 1000 == 0:
            print("Generating image event ...", i)
 
        h1.Reset()
        h2.Reset()
        # generate random means in range [3,7] to be not too much on the border
        f1.SetParameter(1, ROOT.gRandom.Uniform(3, 7))
        f1.SetParameter(3, ROOT.gRandom.Uniform(3, 7))
        f2.SetParameter(1, ROOT.gRandom.Uniform(3, 7))
        f2.SetParameter(3, ROOT.gRandom.Uniform(3, 7))
 
        h1.FillRandom("f1", nRndmEvts)
        h2.FillRandom("f2", nRndmEvts)
 
        for k in range(nh):
            for l in range(nw):
                m = k * nw + l
                # add some noise in each bin
                x1[m] = h1.GetBinContent(k + 1, l + 1) + ROOT.gRandom.Gaus(0, pixelNoise)
                x2[m] = h2.GetBinContent(k + 1, l + 1) + ROOT.gRandom.Gaus(0, pixelNoise)
 
        sgn.Fill()
        bkg.Fill()
 
    sgn.Write()
    bkg.Write()
 
    print("Signal and background tree with images data written to the file %s", f.GetName())
    sgn.Print()
    bkg.Print()
    f.Close()
 
hasGPU = "tmva-gpu" in ROOT.gROOT.GetConfigFeatures()
hasCPU = "tmva-cpu" in ROOT.gROOT.GetConfigFeatures()
 
nevt = 1000    # use a larger value to get better results
 
if (not hasCPU and not hasGPU) :
    ROOT.Warning("TMVA_CNN_Classificaton","ROOT is not supporting tmva-cpu and tmva-gpu skip using TMVA-DNN and TMVA-CNN")
    useTMVACNN = False
    useTMVADNN = False
 
if not "tmva-pymva" in ROOT.gROOT.GetConfigFeatures():
    useKerasCNN = False
    usePyTorchCNN = False
else:
    TMVA.PyMethodBase.PyInitialize()
 
if not useTMVACNN:
    ROOT.Warning(
        "TMVA_CNN_Classificaton",
        "TMVA is not build with GPU or CPU multi-thread support. Cannot use TMVA Deep Learning for CNN",
    )
 
writeOutputFile = True
 
num_threads = 4  # use max 4 threads
max_epochs = 10  # maximum number of epochs used for training
 
 
# do enable MT running
if "imt" in ROOT.gROOT.GetConfigFeatures():
    ROOT.EnableImplicitMT(num_threads)
    ROOT.gSystem.Setenv("OMP_NUM_THREADS", "1")  # switch OFF MT in OpenBLAS
    print("Running with nthreads  = {}".format(ROOT.GetThreadPoolSize()))
else:
    print("Running in serial mode since ROOT does not support MT")
 
 
 
 
outputFile = None
if writeOutputFile:
    outputFile = TFile.Open("TMVA_CNN_ClassificationOutput.root", "RECREATE")
 
 
## Create TMVA Factory
 
# Create the Factory class. Later you can choose the methods
# whose performance you'd like to investigate.
 
# The factory is the major TMVA object you have to interact with. Here is the list of parameters you need to pass
 
# - The first argument is the base of the name of all the output
#   weight files in the directory weight/ that will be created with the
#    method parameters
 
# - The second argument is the output file for the training results
 
# - The third argument is a string option defining some general configuration for the TMVA session.
# For example all TMVA output can be suppressed by removing the "!" (not) in front of the "Silent" argument in the
# option string
 
# - note that we disable any pre-transformation of the input variables and we avoid computing correlations between
# input variables
 
 
factory = TMVA.Factory(
    "TMVA_CNN_Classification",
    outputFile,
    V=False,
    ROC=True,
    Silent=False,
    Color=True,
    AnalysisType="Classification",
    Transformations=None,
    Correlations=False,
)
 
 
## Declare DataLoader(s)
 
# The next step is to declare the DataLoader class that deals with input variables
 
# Define the input variables that shall be used for the MVA training
# note that you may also use variable expressions, which can be parsed by TTree::Draw( "expression" )]
 
# In this case the input data consists of an image of 16x16 pixels. Each single pixel is a branch in a ROOT TTree
 
loader = TMVA.DataLoader("dataset")
 
 
## Setup Dataset(s)
 
# Define input data file and signal and background trees
 
 
imgSize = 16 * 16
inputFileName = "images_data_16x16.root"
 
# if the input file does not exist create it
if ROOT.gSystem.AccessPathName(inputFileName):
    MakeImagesTree(nevt, 16, 16)
 
inputFile = TFile.Open(inputFileName)
if inputFile is None:
    ROOT.Warning("TMVA_CNN_Classification", "Error opening input file %s - exit", inputFileName.Data())
 
 
# inputFileName = "tmva_class_example.root"
 
 
# --- Register the training and test trees
 
signalTree = inputFile.Get("sig_tree")
backgroundTree = inputFile.Get("bkg_tree")
 
nEventsSig = signalTree.GetEntries()
nEventsBkg = backgroundTree.GetEntries()
 
# global event weights per tree (see below for setting event-wise weights)
signalWeight = 1.0
backgroundWeight = 1.0
 
# You can add an arbitrary number of signal or background trees
loader.AddSignalTree(signalTree, signalWeight)
loader.AddBackgroundTree(backgroundTree, backgroundWeight)
 
## add event variables (image)
## use new method (from ROOT 6.20 to add a variable array for all image data)
loader.AddVariablesArray("vars", imgSize)
 
# Set individual event weights (the variables must exist in the original TTree)
#    for signal    : factory->SetSignalWeightExpression    ("weight1*weight2");
#    for background: factory->SetBackgroundWeightExpression("weight1*weight2");
# loader->SetBackgroundWeightExpression( "weight" );
 
# Apply additional cuts on the signal and background samples (can be different)
mycuts = ""  # for example: TCut mycuts = "abs(var1)<0.5 && abs(var2-0.5)<1";
mycutb = ""  # for example: TCut mycutb = "abs(var1)<0.5";
 
# Tell the factory how to use the training and testing events
# If no numbers of events are given, half of the events in the tree are used
# for training, and the other half for testing:
#    loader.PrepareTrainingAndTestTree( mycut, "SplitMode=random:!V" );
# It is possible also to specify the number of training and testing events,
# note we disable the computation of the correlation matrix of the input variables
 
nTrainSig = 0.8 * nEventsSig
nTrainBkg = 0.8 * nEventsBkg
 
# build the string options for DataLoader::PrepareTrainingAndTestTree
 
loader.PrepareTrainingAndTestTree(
    mycuts,
    mycutb,
    nTrain_Signal=nTrainSig,
    nTrain_Background=nTrainBkg,
    SplitMode="Random",
    SplitSeed=100,
    NormMode="NumEvents",
    V=False,
    CalcCorrelations=False,
)
 
 
# DataSetInfo              : [dataset] : Added class "Signal"
#    : Add Tree sig_tree of type Signal with 10000 events
#    DataSetInfo              : [dataset] : Added class "Background"
#        : Add Tree bkg_tree of type Background with 10000 events
 
# signalTree.Print();
 
# Booking Methods
 
# Here we book the TMVA methods. We book a Boosted Decision Tree method (BDT)
 
 
# Boosted Decision Trees
if useTMVABDT:
    factory.BookMethod(
        loader,
        TMVA.Types.kBDT,
        "BDT",
        V=False,
        NTrees=400,
        MinNodeSize="2.5%",
        MaxDepth=2,
        BoostType="AdaBoost",
        AdaBoostBeta=0.5,
        UseBaggedBoost=True,
        BaggedSampleFraction=0.5,
        SeparationType="GiniIndex",
        nCuts=20,
    )
 
 
#### Booking Deep Neural Network
 
# Here we book the DNN of TMVA. See the example TMVA_Higgs_Classification.C for a detailed description of the
# options
 
if useTMVADNN:
    layoutString = ROOT.TString(
        "DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,BNORM,DENSE|100|RELU,DENSE|1|LINEAR"
    )
 
    # Training strategies
    # one can catenate several training strings with different parameters (e.g. learning rates or regularizations
    # parameters) The training string must be concatenated with the `|` delimiter
    trainingString1 = ROOT.TString(
        "LearningRate=1e-3,Momentum=0.9,Repetitions=1,"
        "ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,"
        "WeightDecay=1e-4,Regularization=None,"
        "Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0."
    )  # + "|" + trainingString2 + ...
    trainingString1 += ",MaxEpochs=" + str(max_epochs)
 
    # Build now the full DNN Option string
    dnnMethodName = "TMVA_DNN_CPU"
 
    # use GPU if available
    dnnOptions = "CPU"
    if hasGPU :
        dnnOptions = "GPU"
        dnnMethodName = "TMVA_DNN_GPU"
 
    factory.BookMethod(
        loader,
        TMVA.Types.kDL,
        dnnMethodName,
        H=False,
        V=True,
        ErrorStrategy="CROSSENTROPY",
        VarTransform=None,
        WeightInitialization="XAVIER",
        Layout=layoutString,
        TrainingStrategy=trainingString1,
        Architecture=dnnOptions
    )
 
 
### Book Convolutional Neural Network in TMVA
 
# For building a CNN one needs to define
 
# -  Input Layout :  number of channels (in this case = 1)  | image height | image width
# -  Batch Layout :  batch size | number of channels | image size = (height*width)
 
# Then one add Convolutional layers and MaxPool layers.
 
# -  For Convolutional layer the option string has to be:
# - CONV | number of units | filter height | filter width | stride height | stride width | padding height | paddig
# width | activation function
 
# - note in this case we are using a filer 3x3 and padding=1 and stride=1 so we get the output dimension of the
# conv layer equal to the input
 
# - note we use after the first convolutional layer a batch normalization layer. This seems to help significantly the
# convergence
 
# - For the MaxPool layer:
# - MAXPOOL  | pool height | pool width | stride height | stride width
 
# The RESHAPE layer is needed to flatten the output before the Dense layer
 
# Note that to run the CNN is required to have CPU  or GPU support
 
 
if useTMVACNN:
    # Training strategies.
    trainingString1 = ROOT.TString(
        "LearningRate=1e-3,Momentum=0.9,Repetitions=1,"
        "ConvergenceSteps=5,BatchSize=100,TestRepetitions=1,"
        "WeightDecay=1e-4,Regularization=None,"
        "Optimizer=ADAM,DropConfig=0.0+0.0+0.0+0.0"
    )
    trainingString1 += ",MaxEpochs=" + str(max_epochs)
 
    ## New DL (CNN)
    cnnMethodName = "TMVA_CNN_CPU"
    cnnOptions = "CPU"
    # use GPU if available
    if hasGPU:
        cnnOptions = "GPU"
        cnnMethodName = "TMVA_CNN_GPU"
 
    factory.BookMethod(
        loader,
        TMVA.Types.kDL,
        cnnMethodName,
        H=False,
        V=True,
        ErrorStrategy="CROSSENTROPY",
        VarTransform=None,
        WeightInitialization="XAVIER",
        InputLayout="1|16|16",
        Layout="CONV|10|3|3|1|1|1|1|RELU,BNORM,CONV|10|3|3|1|1|1|1|RELU,MAXPOOL|2|2|1|1,RESHAPE|FLAT,DENSE|100|RELU,DENSE|1|LINEAR",
        TrainingStrategy=trainingString1,
        Architecture=cnnOptions,
    )
 
 
### Book Convolutional Neural Network in Keras using a generated model
 
 
if usePyTorchCNN:
    ROOT.Info("TMVA_CNN_Classification", "Using Convolutional PyTorch Model")
    pyTorchFileName = str(ROOT.gROOT.GetTutorialDir())
    pyTorchFileName += "/tmva/PyTorch_Generate_CNN_Model.py"
    # check that pytorch can be imported and file defining the model exists
    torch_spec = importlib.util.find_spec("torch")
    if torch_spec is not None and os.path.exists(pyTorchFileName):
        #cmd = str(ROOT.TMVA.Python_Executable()) + "  " + pyTorchFileName
        #os.system(cmd)
        #import PyTorch_Generate_CNN_Model
        ROOT.Info("TMVA_CNN_Classification", "Booking PyTorch CNN model")
        factory.BookMethod(
            loader,
            TMVA.Types.kPyTorch,
            "PyTorch",
            H=True,
            V=False,
            VarTransform=None,
            FilenameModel="PyTorchModelCNN.pt",
            FilenameTrainedModel="PyTorchTrainedModelCNN.pt",
            NumEpochs=max_epochs,
            BatchSize=100,
            UserCode=str(pyTorchFileName)
        )
    else:
        ROOT.Warning(
            "TMVA_CNN_Classification",
            "PyTorch is not installed or model building file is not existing - skip using PyTorch",
        )
 
if useKerasCNN:
    ROOT.Info("TMVA_CNN_Classification", "Building convolutional keras model")
    # create python script which can be executed
    # create 2 conv2d layer + maxpool + dense
    import tensorflow
    from tensorflow.keras.models import Sequential
    from tensorflow.keras.optimizers import Adam
 
    # from keras.initializers import TruncatedNormal
    # from keras import initializations
    from tensorflow.keras.layers import Input, Dense, Dropout, Flatten, Conv2D, MaxPooling2D, Reshape
 
    # from keras.callbacks import ReduceLROnPlateau
    model = Sequential()
    model.add(Reshape((16, 16, 1), input_shape=(256,)))
    model.add(Conv2D(10, kernel_size=(3, 3), kernel_initializer="TruncatedNormal", activation="relu", padding="same"))
    model.add(Conv2D(10, kernel_size=(3, 3), kernel_initializer="TruncatedNormal", activation="relu", padding="same"))
    # stride for maxpool is equal to pool size
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Flatten())
    model.add(Dense(64, activation="tanh"))
    # model.add(Dropout(0.2))
    model.add(Dense(2, activation="sigmoid"))
    model.compile(loss="binary_crossentropy", optimizer=Adam(learning_rate=0.001), weighted_metrics=["accuracy"])
    model.save("model_cnn.h5")
    model.summary()
 
    if not os.path.exists("model_cnn.h5"):
        raise FileNotFoundError("Error creating Keras model file - skip using Keras")
    else:
        # book PyKeras method only if Keras model could be created
        ROOT.Info("TMVA_CNN_Classification", "Booking convolutional keras model")
        factory.BookMethod(
            loader,
            TMVA.Types.kPyKeras,
            "PyKeras",
            H=True,
            V=False,
            VarTransform=None,
            FilenameModel="model_cnn.h5",
            FilenameTrainedModel="trained_model_cnn.h5",
            NumEpochs=max_epochs,
            BatchSize=100,
            GpuOptions="allow_growth=True",
        )  # needed for RTX NVidia card and to avoid TF allocates all GPU memory
 
 
 
## Train Methods
 
factory.TrainAllMethods()
 
## Test and Evaluate Methods
 
factory.TestAllMethods()
 
factory.EvaluateAllMethods()
 
## Plot ROC Curve
 
c1 = factory.GetROCCurve(loader)
c1.Draw()
 
# close outputfile to save output file
outputFile.Close()

Author

Harshal Shende

Definition in file TMVA_CNN_Classification.py.