VGG16

VGGNet是牛津大学计算机视觉组(Visual Geometry Group)和Google DeepMind公司的研究员一起研发的深度卷积神经网络,它探索了卷积神经网络的深度与其性能之间的关系,通过反复堆叠33的小型卷积核和22的最大池化层,成功地构筑了16~19层深的卷积神经网络。VGGNet相比之前state-of-the-art的网络结构,错误率大幅下降,VGGNet论文中全部使用了33的小型卷积核和22的最大池化核,通过不断加深网络结构来提升性能。

Mirror Metadata

  • Hugging Face repo: shadow-cann/hispark-modelzoo-vgg16
  • Portal model id: ht96f9b50o00
  • Created at: 2025-11-17 11:25:12
  • Updated at: 2025-11-29 14:49:58
  • Category: 计算机视觉

Framework

  • PyTorch

Supported OS

  • OpenHarmony
  • Linux

Computing Power

  • Hi3403V100 SVP_NNN
  • Hi3403V100 NNN

Tags

  • 分类

Detail Parameters

  • 输入: 224x224
  • 参数量: 138.358M
  • 计算量: 31.007GFLOPs

Files In This Repo

  • vgg16.onnx (源模型 / 源模型下载; 源模型 / 源模型元数据; 编译模型 / OM 元数据 / a8w8)
  • vgg16-397923af.pth (源模型 / 源模型下载; 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

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: 1712668134146051_panda1.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