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

Mostrar otras versiones (2)

<!--HTML-->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 conductin...

Descripción completa

Detalles Bibliográficos
Autor principal: An, Sitong
Lenguaje:eng
Publicado: 2021
Materias:
Conferences
Acceso en línea:http://cds.cern.ch/record/2766903
_version_ 1780971246701248512
author An, Sitong
author_facet An, Sitong
author_sort An, Sitong
collection CERN
description <!--HTML-->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.
id cern-2766903
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
record_format invenio
spelling cern-27669032022-11-02T22:25:53Zhttp://cds.cern.ch/record/2766903engAn, SitongC++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA25th International Conference on Computing in High Energy & Nuclear PhysicsConferences<!--HTML-->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.oai:cds.cern.ch:27669032021
spellingShingle Conferences
An, Sitong
C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA
title C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA
title_full C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA
title_fullStr C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA
title_full_unstemmed C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA
title_short C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA
title_sort c++ code generation for fast inference of deep learning models in root/tmva
topic Conferences
url http://cds.cern.ch/record/2766903
work_keys_str_mv AT ansitong ccodegenerationforfastinferenceofdeeplearningmodelsinroottmva
AT ansitong 25thinternationalconferenceoncomputinginhighenergynuclearphysics

Ejemplares similares