CoolFace
Modelpublic

shadow-cann/hispark-modelzoo-vdsr

sourceHugging Faceupdated 7d agoView on Hugging Face
0likes
Model Card

VDSR

VDSR（Very Deep Super-Resolution Network）是一种20层深度卷积神经网络，通过残差学习实现图像超分辨率重建。

Mirror Metadata

  • —Hugging Face repo: shadow-cann/hispark-modelzoo-vdsr
  • —Portal model id: i9kll1a96k00
  • —Created at: 2025-12-25 20:56:31
  • —Updated at: 2025-12-30 20:02:18
  • —Category: 计算机视觉

Framework

  • —PyTorch

Supported OS

  • —OpenHarmony
  • —Linux

Computing Power

  • —Hi3403V100 SVP_NNN
  • —Hi3403V100 NNN

Tags

  • —图像超分

Detail Parameters

  • —输入: 516x516
  • —参数量: 664.704M
  • —计算量: 354.611GFLOPs

Files In This Repo

  • —vdsr.om (编译模型 / A8W8 / A8W8)
  • —vdsrfp16Hi3403V100-NNN.om (编译模型 / FP16 / FP16)
  • —vdsr.zip (源模型 / 源模型下载)
  • —SVPNNNPC_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=i9kll1a96k00
  • —Upstream repository: https://gitee.com/HiSpark/modelzoo/tree/master/samples/built-in/super_resolution/VDSR
  • —License reference: https://github.com/Lornatang/VDSR-PyTorch/blob/master/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.
  • —Cover image: 1719627344314369_VDSRdemo.png