YOLOv3: An Incremental Improvement |
您所在的位置:网站首页 › 百度学术求助论文 › YOLOv3: An Incremental Improvement |
来自
arXiv.org
喜欢
11
阅读量: 85894 作者: J Redmon,A Farhadi 展开 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 展开 关键词: Computer Science - Computer Vision and Pattern Recognition DOI: 10.48550/arXiv.1804.02767 被引量: 211 年份: 2018 |
今日新闻 |
推荐新闻 |
CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3 |