Unverified60% confidenceFactExact time
Since the release of the first version in 2016, the YOLO series has undergone multiple iterations from YOLOv1 to YOLOv10, achieving inference speeds of 100+ FPS.
2
Sources
60%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedYOLOv8 模型家族从 YOLOv8n（约 3.2M 参数）到 YOLOv8x（约 68M 参数）覆盖从树莓派到高性能 GPU 的硬件谱系69% similarUnverifiedYOLOv8m is the medium-scale version of the YOLOv8 series released by Ultralytics in 2023, belonging to the single-stage object detection architecture, and introduces an anchor-free detection head and decoupled classification/regression branches.68% similarUnverifiedYOLOv8 can achieve hundreds of frames per second on modern GPUs.66% similarUnverifiedYOLOv8 offers different model sizes—n/s/m/l/x—allowing a trade-off between accuracy and speed.66% similarUnverified相比YOLOv8，YOLOv11在模型架构上引入了C3k2模块和SPPF改进，在保持检测精度的同时降低了参数量和计算量65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/518344API
curl https://kongchang.com/api/v1/knowledge/claims/518344MCP
get_claim(id=518344)