shadow-cann/hispark-modelzoo-yolov4

YOLOv4

YOLOv4 是一种高性能的 one-stage 目标检测模型。相比 YOLOv3，YOLOv4 采用了 CSPDarknet53 作为 backbone 进行特征提取，该网络结合了跨金字塔池化结构和路径聚合网络，在精度和速度上均有显著提升。

Mirror Metadata

• Hugging Face repo: shadow-cann/hispark-modelzoo-yolov4
• Portal model id: kuerjmbgts00
• Created at: 2026-09-15 09:27:15
• Updated at: 2026-09-15 15:27:11
• Category: 计算机视觉

Framework

• PyTorch

Supported OS

• OpenHarmony
• Linux

Computing Power

• Hi3403V100 SVP_NNN
• Hi3403V100 NNN

Tags

• 目标检测

Detail Parameters

• 输入: 608x608
• 参数量: 64.330M
• 计算量: 157.842GFLOPs

Files In This Repo

• yolov4_dpico.om (编译模型 / OM 元数据 / A16W8)
• yolov4_dlite_fp16.om (编译模型 / FP16 / FP16)
• yolov4.pth (源模型 / 源模型下载)
• yolov4.onnx (源模型 / 源模型下载)
• SVP_NNN_PC_V1.0.6.0.tgz (工具链 / 工具链)

Upstream Links

• Portal card: https://gitbubble.github.io/hisilicon-developer-portal-mirror/model-detail.html?id=kuerjmbgts00
• Upstream repository: https://gitcode.com/HiSpark/modelzoo/tree/master/samples/built-in/detection/yolov4
• License reference: https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/master/License.txt

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.
• Cover image: 1712131749773315_yolov4.jpg