TMVA_SOFIE_Keras_HiggsModel¶

This macro run the SOFIE parser on the Keras model obtaining running TMVA_Higgs_Classification.C You need to run that macro before this one

Author: Lorenzo Moneta
This notebook tutorial was automatically generated with ROOTBOOK-izer from the macro found in the ROOT repository on Wednesday, July 16, 2025 at 05:07 AM.

In [1]:

using namespace TMVA::Experimental;

Arguments are defined.

In [2]:

const char * modelFile = "Higgs_trained_model.h5";

check if the input file exists

In [3]:

if (gSystem->AccessPathName(modelFile)) {
    Error("TMVA_SOFIE_RDataFrame","You need to run TMVA_Higgs_Classification.C to generate the Keras trained model");
    return;
}

Error in <TMVA_SOFIE_RDataFrame>: You need to run TMVA_Higgs_Classification.C to generate the Keras trained model

parse the input Keras model into RModel object

In [4]:

SOFIE::RModel model = SOFIE::PyKeras::Parse(modelFile);

TString modelHeaderFile = modelFile;
modelHeaderFile.ReplaceAll(".h5",".hxx");

input_line_58:2:31: error: 'PyKeras' is not a class, namespace, or enumeration
 SOFIE::RModel model = SOFIE::PyKeras::Parse(modelFile);
                              ^
input_line_58:2:31: note: 'PyKeras' declared here

Generating inference code

In [5]:

model.Generate();
model.OutputGenerated(std::string(modelHeaderFile));

input_line_60:2:3: error: use of undeclared identifier 'model'
 (model.Generate())
  ^
Error in <HandleInterpreterException>: Error evaluating expression (model.Generate())
Execution of your code was aborted.

copy include in $ROOTSYS/tutorials

In [6]:

std::cout << "include is in " << gROOT->GetIncludeDir() << std::endl;

include is in /github/home/ROOT-CI/build/include/