Machine learning with tensorflow

I’m trying to start research with machine learning(with tensorflow). I want to discriminate signal and background with waveform.
So, I have to handle with root format file but I just heard something that I should convert root file to h5 format for machine learning.
I’ve searched a lot and lot on google about “convert root to h5” and I found something like root_pandas/root_numpy library and uproot something. But I don’t know how to start exactly and apply with my data files. I cannot get any ideas though I read the git page.
If you guys know about these machine learning 101 in particle physics experiment(especially machine learning with root file) please share me some good study materials.
Ah, and please teach me about how to use uproot to convert file format.

Please read tips for efficient and successful posting and posting code

ROOT Version: Not Provided
Platform: Not Provided
Compiler: Not Provided

uproot and root_numpy are packages which are not part of ROOT, but I am sure you can find information the Web on how to use those packages.
In ROOT, you can do, within the TMVA package, use Tensorflow Keras via the TMVA Keras interface.
In this case you do not need to convert any ROOT files to some other format for the input data.
The package reads ROOT files and convert internally to numpty arrays that re provided as input to Tensorflow.
We have tutorial examples in

and an example using C++ is

Best regards


This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.