Unverified50% confidenceFactExact time
YOLOv5和YOLOv8都提供从nano(n)到extra-large(x)的多个规模变体
1
Sources
50%
Confidence
Long-term
Relevance
9/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedYOLOv8 模型分为 nano 到 x 多个规格，YOLOv8s 在边缘设备上可实现实时推理78% similarUnverifiedYOLOv8 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68% similarUnverifiedYOLOv3引入多尺度预测和残差网络；YOLOv4集成了CSPNet和PANet。67% similarUnverifiedYOLOv3采用多尺度特征金字塔（FPN）66% similarUnverifiedYOLOv8-nano模型在中端NPU上可实现30FPS以上的推理帧率66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/838142API
curl https://kongchang.com/api/v1/knowledge/claims/838142MCP
get_claim(id=838142)