UFLDv2

UFLDv2(Ultra-Fast-Lane-Detection-v2)是一种基于混合锚点驱动有序分类方法的车道线检测模型。该模型采用 ResNet18 作为骨干网络,配合 ParsingNet 解析网络,在保持超高推理速度的同时实现了良好的车道线检测精度。

Mirror Metadata

  • Hugging Face repo: shadow-cann/hispark-modelzoo-ufldv2
  • Portal model id: ku57c46cj400
  • Created at: 2026-09-14 11:00:33
  • Updated at: 2026-09-15 15:27:10
  • Category: 计算机视觉

Framework

  • PyTorch

Supported OS

  • Linux

Computing Power

  • Hi3516CV610

Tags

  • 车道线检测

Detail Parameters

  • 输入: 800 x 320
  • 参数量: 96.365M
  • 计算量: 18.753 GFLOPs

Files In This Repo

  • ufldv2.om (编译模型 / A8W8 / A8W8)
  • ufldv2.onnx (源模型 / 源模型下载)

Upstream Links

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: 1767233107918850_cover.jpg
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support