YOLOv6 v3 .0:一个全面的测试
YOLOv6 v3.0: A Full-Scale Reloading
摘要:
自从我们的前两个版本发布以来,YOLO社区一直处于高涨的状态!随着2023年兔年农历新年的到来,我们对YOLOv 6的网络架构和训练方案进行了大量新的改进。此版本被标识为YOLOv 6 v3.0。为了了解性能,我们的YOLOv 6-N在COCO数据集上达到37.5%的AP,吞吐量为1187 FPS,使用NVIDIA Tesla T4 GPU进行测试。YOLOv 6-S在484 FPS下达到45.0% AP,优于相同规模的其他主流检测器(YOLOv 5-S,YOLOv 8-S,YOLOX-S和PPYLOE-S)。而YOLOv 6-M/L在推理速度相近的情况下,也取得了比其他检测器更好的准确率(分别为50.0%/52.8%)。此外,通过扩展的主干和颈部设计,我们的YOLOv 6-L 6实现了最先进的实时精度。大量的实验仔细进行,以验证每个改进组件的有效性。我们的代码可在https://github.com/meituan/YOLOv6上获得。
英文摘要:
The YOLO community has been in high spirits since our first two releases! By the advent of Chinese New Year 2023, which sees the Year of the Rabbit, we refurnish YOLOv6 with numerous novel enhancements on the network architecture and the training scheme. This release is identified as YOLOv6 v3.0. For a glimpse of performance, our YOLOv6-N hits 37.5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 45.0% AP at 484 FPS, outperforming other mainstream detectors at the same scale (YOLOv5-S, YOLOv8-S, YOLOX-S and PPYOLOE-S). Whereas, YOLOv6-M/L also achieve better accuracy performance (50.0%/52.8% respectively) than other detectors at a similar inference speed. Additionally, with an extended backbone and neck design, our YOLOv6-L6 achieves the state-of-the-art accuracy in real-time. Extensive experiments are carefully conducted to validate the effectiveness of each improving component. Our code is made available at https://github.com/meituan/YOLOv6.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。