shadow-cann/hispark-modelzoo-efficientnetv2

EfficientNetV2

EfficientNetV2是一系列图像分类模型，与现有技术相比，其实现了更好的参数效率和更快的训练速度。基于EfficientNetV1，Efficient NetV2模型使用神经架构搜索（NAS）来联合优化模型大小和训练速度，并以更快的训练和推理速度进行扩展。

Mirror Metadata

• —Hugging Face repo: shadow-cann/hispark-modelzoo-efficientnetv2
• —Portal model id: ko3p9r40j400
• —Created at: 2026-08-26 16:15:43
• —Updated at: 2026-09-01 16:13:06
• —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: 288x288
• —参数量: 25.530M
• —计算量: 8.235GFLOPs

Files In This Repo

• —efficientnetv2.om (编译模型 / A8W8 / A8W8)
• —efficientnetv2FP16Hi3403V100-NNN.om (编译模型 / FP16 / FP16)
• —efficientnetv2.onnx (源模型 / 源模型下载)
• —efficientnetv2tagc-3620981a.pth (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=ko3p9r40j400
• —Upstream repository: https://gitcode.com/HiSpark/modelzoo/tree/master/samples/built-in/classification/EfficientNetV2
• —License reference: https://github.com/huggingface/pytorch-image-models/blob/main/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: 1700943102148611_eff.png