C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA-Reference-Cited by-同舟云学术

C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA

Published:2021 Issue: Volume:251 Page:03040
ISSN:2100-014X
Container-title:EPJ Web of Conferences
language:
Short-container-title:EPJ Web Conf.

Author:

An Sitong,Moneta Lorenzo

Abstract

We report the latest development in ROOT/TMVA, a new system that takes trained ONNX deep learning models and emits C++ code that can be easily included and invoked for fast inference of the model, with minimal dependency. We present an overview of the current solutions for conducting inference in C++ production environment, discuss the technical details and examples of the generated code, and demonstrates its development status with a preliminary benchmark against popular tools.

Publisher

EDP Sciences

Link

https://www.epj-conferences.org/10.1051/epjconf/202125103040/pdf

Reference20 articles.

1. Hoecker A., Speckmayer P., Stelzer J., Therhaag J., von Toerne E., Voss H., Backes M., Carli T., Cohen O., Christov A. et al., TMVA - Toolkit for Multivariate Data Analysis (2007), physics/0703039

2. Brun R., Rademakers F., Nucl.Instrum.Meth.A 389 (1997) 81–86

3. Chatrchyan S. et al. (CMS), Phys. Lett. B710, 403 (2012), 1202.1487

4. The ATLAS collaboration, Evidence for Higgs Boson Decays to the Final State with the ATLAS Detector (2013)

5. Chatrchyan S., Khachatryan V., Sirunyan A., Tumasyan A., Adam W., Aguilo E., Bergauer T., Dragicevic M., Erö J., Fabjan C. et al., Physics Letters B 716, 30–61 (2012)

Cited by 129 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA;Journal of Physics: Conference Series;2023-02-01

2. Optimal Choices in Decision Supporting System for Network Reservoir Operation;Water;2022-12-14

3. In Vitro Propagation and Phytochemistry of Thymol-Producing Plants from a Horticultural Form of Thymus × josephi-angeli Mansanet & Aguil. (Lamiaceae);Horticulturae;2022-12-13

4. Predicting Fraud in Financial Payment Services through Optimized Hyper-Parameter-Tuned XGBoost Model;Mathematics;2022-12-09

5. Development of early age autogenous and thermal strains of alkali-activated slag-fly ash pastes;Frontiers in Built Environment;2022-12-06