关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
JDOpenISCT
/
FaceX-Zoo
mirror of https://github.com/JDAI-CV/FaceX-Zoo
Not watched
8
17
Fork 12
Code
Releases 0 Wiki Activity
Issues 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
199 Commits
1 Branch
164 MiB
18 Download
 
 
 
Branch: main
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'main'
${ noResults }
FaceX-Zoo/head
wangjun492 2f97a0ef2d swing 2 years ago
..
AM_Softmax.py fix tensor type byte warning 3 years ago
AdaCos.py add MagFace 3 years ago
AdaM_Softmax.py fix tensor type byte warning 3 years ago
ArcFace.py fix tensor type byte warning 3 years ago
ArcNegFace.py add arcnegface loss 3 years ago
CircleLoss.py fix tensor type byte warning 3 years ago
CurricularFace.py add MagFace 3 years ago
MV_Softmax.py add MagFace 3 years ago
MagFace.py fix tensor type byte warning 3 years ago
NPCFace.py add MagFace 3 years ago
SST_Prototype.py add MagFace 3 years ago
head_def.py swing 2 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

SST(Semi-Siamese Training)是一种针对浅层数据的人脸识别模型训练方法，所训练模型为一对半孪生网络，包括一个主模型和一个副模型，每次迭代时网络输入为同一ID的两张人脸图像(注册照和现场照)，副模型从注册照中提取人脸特征并构成一个动态的特征队列，随着训练进行同步更新，根据主模型从现场照中提取的人脸特征和动态特征队列计算损失函数，得到损失值后主模型采用随机梯度下降的方式进行更新，副模型基于当前模型状态与主模型采用滑动平均的方式进行更新，训练完成后主模型用于人脸识别测试。

Text Pickle Python

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit