ultralytics/yolov5: v6.0 - YOLOv5n 'Nano' models, Roboflow integration, TensorFlow export, OpenCV DNN support

Jocher, Glenn; Stoken, Alex; Chaurasia, Ayush; Borovec, Jirka; , NanoCode; , TaoXie; Kwon, Yonghye; Michael, Kalen; Liu, Changyu,; Fang, Jiacong; Abhiram, Abhiram; , Laughing; , tkianai; , yxNONG; Skalski, Piotr; Marie Hogan, A.; Nadar, Jebastin; , imyhxy; Mammana, Lorenzo; , AlexWang; Fati, Cristi; P. Montes, Diego; Hájek, Jan; Diaconu, Laurentiu; Thanh Minh, Mai; Marc, Marc; , albinxavi; , fatih; Oleg, Oleg; , wanghaoyang

doi:10.5281/zenodo.5563715

Public

ultralytics/yolov5: v6.0 - YOLOv5n 'Nano' models, Roboflow integration, TensorFlow export, OpenCV DNN support

Published in Zenodo (CERN European Organization for Nuclear Research) • Oct 12, 2021

Authors:

Glenn Jocher

Alex Stoken

Ayush Chaurasia

Abstract

This release incorporates many new features and bug fixes (465 PRs from 73 contributors) since our last release v5.0 in April, brings architecture tweaks, and also introduces new P5 and P6 'Nano' models: YOLOv5n and YOLOv5n6. Nano models maintain the YOLOv5s depth multiple of 0.33 but reduce the YOL...

Subject

Artificial intelligence

Artificial neural network

Computer science

Research Assistant

AI chat, annotations, notes & similar papers

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!