CodaLab Competitions: An open source platform to organize scientific challenges - Laboratoire Interdisciplinaire des Sciences du Numérique Access content directly
Reports (Technical Report) Year : 2022

CodaLab Competitions: An open source platform to organize scientific challenges

Abstract

CodaLab Competitions is an open source web platform designed to help data scientists and research teams to crowd-source the resolution of machine learning problems through the organization of competitions, also called challenges or contests. CodaLab Competitions provides useful features such as multiple phases, results and code submissions, multi-score leaderboards, and jobs running inside Docker containers. The platform is very flexible and can handle large scale experiments, by allowing organizers to upload large datasets and provide their own CPU or GPU compute workers.
Fichier principal
Vignette du fichier
CodaLab_Competitions_report.pdf (259.02 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03629462 , version 1 (04-04-2022)

Identifiers

  • HAL Id : hal-03629462 , version 1

Cite

Adrien Pavao, Isabelle Guyon, Anne-Catherine Letournel, Xavier Baró, Hugo Escalante, et al.. CodaLab Competitions: An open source platform to organize scientific challenges. [Technical Report] Université Paris-Saclay, FRA. 2022. ⟨hal-03629462⟩
534 View
574 Download

Share

Gmail Facebook X LinkedIn More