shadow-cann/hispark-modelzoo-densenet121

DenseNet121

DenseNet 针对 ResNet 的冗余结构提出了改进：让网络中的每一层和前面的所有层相连，同时把每一层设计的比较窄，使每一层学到的特征变少从而降低冗余。除了减少参数量之外，该结构还有减轻梯度消失问题、增强特征传播等优点。

Mirror Metadata

• Hugging Face repo: shadow-cann/hispark-modelzoo-densenet121
• Portal model id: j3mmucroso00
• Created at: 2026-03-16 20:23:49
• Updated at: 2026-03-26 09:35:38
• 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: 8.04M
• 计算量: 6.369GFLOPs

Files In This Repo

• densenet121_om-A8W8.om (编译模型 / A8W8)
• densenet121.om (编译模型 / FP16; 编译模型 / OM 元数据 / A8W8)
• densenet121.onnx (源模型 / 源模型下载; 源模型 / 源模型元数据)
• densenet121-a639ec97.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

• Portal card: https://gitbubble.github.io/hisilicon-developer-portal-mirror/model-detail.html?id=j3mmucroso00
• Upstream repository: https://gitee.com/HiSpark/modelzoo/tree/master/samples/built-in/classification/DenseNet121
• License reference: https://github.com/pytorch/vision/blob/v0.14.0/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: 1700942504460291_des.png