shadow-cann/hispark-modelzoo-yolov10s

YOLOv10s

YOLOv10 引入了一种新的实时目标检测方法，解决了以前YOLO 版本在后处理和模型架构方面的不足。通过消除非最大抑制NMS和优化各种模型组件，YOLOv10 显著降低了计算开销。本示例基于YOLOv10s。

Mirror Metadata

• Hugging Face repo: shadow-cann/hispark-modelzoo-yolov10s
• Portal model id: j8pjtko0i000
• Created at: 2026-04-01 15:59:40
• Updated at: 2026-04-08 16:07:06
• Category: 计算机视觉

Framework

• PyTorch

Supported OS

• OpenHarmony
• Linux

Computing Power

• Hi3403V100 SVP_NNN

Tags

• 目标检测

Detail Parameters

• 输入: 640x640
• 参数量: 7.291M
• 计算量: 24.073GFLOPs

Files In This Repo

• yolov10s.om (编译模型 / A16W8; 编译模型 / OM 元数据 / A16W8)
• yolov10s_source-model.onnx (源模型 / 源模型下载)
• yolov10s_source-model.pt (源模型 / 源模型下载)
• yolov10s.onnx (源模型 / 源模型元数据)
• yolov10s.pt (源模型 / 源模型元数据)
• SVP_NNN_PC_V1.0.6.0.tgz (附加资源 / 附加资源)

Upstream Links

• Portal card: https://gitbubble.github.io/hisilicon-developer-portal-mirror/model-detail.html?id=j8pjtko0i000
• Upstream repository: https://gitee.com/HiSpark/modelzoo/tree/master/samples/samples_GPL/built-in/yolov10s
• License reference: https://github.com/THU-MIG/yolov10/blob/v1.1/LICENSE

Notes

• This repository was mirrored from the HiSilicon Developer Portal model card and local downloads captured on 2026-03-27.
• File ownership follows the portal card mapping, not just filename similarity.