编码(集合论)
泰坦(火箭家族)
计算机科学
公制(单位)
膨胀
担心
人工智能
算法
计算机视觉
地质学
程序设计语言
工程类
心理学
航空航天工程
精神科
海洋学
集合(抽象数据类型)
焦虑
运营管理
作者
Joseph Redmon,Ali Farhadi
出处
期刊:Cornell University - arXiv
日期:2018-04-08
被引量:6152
摘要
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet, similar performance but 3.8x faster. As always, all the code is online at this https URL
科研通智能强力驱动
Strongly Powered by AbleSci AI