FaceNet
FaceNet 是一种基于深度卷积神经网络的端到端人脸识别与特征嵌入模型。相比传统基于手工特征或分阶段匹配的方法,它通过将人脸图像直接映射为固定维度的紧凑特征向量(Embedding),并采用三元组损失(Triplet Loss)优化特征相似度度量,能有效缩小类内差异、扩大类间距离,兼顾识别精度与推理效率,适用于身份验证、人脸检索、监控安防等大规模人脸识别场景。
Mirror Metadata
- Hugging Face repo: shadow-cann/hispark-modelzoo-facenet
- Portal model id: iapedo790s00
- Created at: 2025-12-29 10:37:55
- Updated at: 2025-12-30 20:02:17
- Category: 计算机视觉
Framework
- PyTorch
Supported OS
- OpenHarmony
- Linux
Computing Power
- Hi3403V100 SVP_NNN
- Hi3403V100 NNN
Tags
- 人脸识别
Detail Parameters
- 输入: 160 x 160
- 参数量: 23.469M
- 计算量: 2.854GFLOPs
Files In This Repo
- facenet_vggface2_static.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=iapedo790s00
- Upstream repository: https://gitee.com/HiSpark/modelzoo/tree/master/samples/built-in/recognition/FaceNet
- License reference: https://github.com/timesler/facenet-pytorch/blob/master/LICENSE.md
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: 1720278245769217_facenet1.jpg
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support