shadow-cann/hispark-modelzoo-vit-b-16

Vit-B-16

Transformer 架构已广泛应用于自然语言处理领域。Vision Transformer（ViT）模型在计算机视觉领域中对CNN的依赖不是必需的，直接将其应用于图像块序列来进行图像分类时，也能得到和目前卷积网络相媲美的准确率。

Mirror Metadata

• Hugging Face repo: shadow-cann/hispark-modelzoo-vit-b-16
• Portal model id: j3vsc0jtvs00
• Created at: 2026-03-17 17:45:49
• 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

• 计算量: 35.994GFLOPS
• 输入: 224x224
• 参数量: 86.568M

Files In This Repo

• vit_base_patch16_224_om-A16W8.om (编译模型 / A16W8)
• vit_base_patch16_224.om (编译模型 / FP16; 编译模型 / OM 元数据 / A16W8)
• vit_base_patch16_224.pt (源模型 / 源模型下载; 源模型 / 源模型元数据)
• vit_base_patch16_224_bs1.onnx (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=j3vsc0jtvs00
• Upstream repository: https://gitee.com/HiSpark/modelzoo/tree/master/samples/built-in/classification/Vit-B-16
• 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: 1701276106686467_20250915111221_469_20.png