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 https://pjreddie.com/yolo/
翻译:我们向 YOLO 展示一些最新消息! 我们做了一连串小小的设计修改来改善它。 我们还训练了这个比上次大一点但更准确的新网络。 虽然它比上次大一点, 但是仍然很快, 不用担心。 在 320x320 YOLOv3 运行22 ms, 时速为28.2 mAP, 准确与 SSD 一样, 速度快三倍。 当我们查看旧的 5 IOU mAP 检测指标YOLOv3 时, 效果相当不错。 它在泰坦X 上实现了51 ms 57.9 mAP@50, 而雷蒂纳Net 在 198 ms 中实现了57.5 mAP@50, 性能相似, 但速度更快3. 8x 。 所有代码都在 https://pjreddie.com/yolo/ 网上 。