资源分类
》 资源 》算法》sphereface_pytorch

sphereface_pytorch

2019-09-16 | |  86 |   0 |   0

|

SphereFace

A PyTorch Implementation of SphereFace. The code can be trained on CASIA-Webface and the best accuracy on LFW is 99.22%.

SphereFace: Deep Hypersphere Embedding for Face Recognition

Train

python train.py

Test

# lfw.tgz to lfw.zip
tar zxf lfw.tgz; cd lfw; zip -r ../lfw.zip *; cd ..

# lfw evaluation
python lfw_eval.py --model model/sphere20a_20171020.pth

Pre-trained models

| Model name | LFW accuracy | Training dataset | |-----------------|--------------|------------------| | 20171020 | 0.9922 | CASIA-WebFace |

equation

equation

phi.png

References

sphereface

上一篇：pytorch-pruning

下一篇：DUC

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...