How to do 1:1 face verification?

wujiyang / Face_Pytorch

face recognition algorithms in pytorch framework, including arcface, cosface, sphereface and so on

Apache License 2.0

808 stars 156 forks source link

How to do 1:1 face verification? #7

Open prnvjb opened 5 years ago

prnvjb commented 5 years ago

Hi, Thanks for this compilation. I'm trying to do one on one face verification specifically based on mobilefacenet. How to compare distance between two feature vectors generated by model. I found loss function for mobilefacenet is arcface. If that is the similarity measure, how to compute arcface loss between two feature vectors. Please share your thoughts. Regards!

wujiyang commented 5 years ago

Arcface loss is just training loss function, it helps to train discriminative feature. If you want to conduct face verification on two images, you can use cosine distance or euclidean distance to evaluate the two feature vectors.

ZZH2950228 commented 4 years ago

do you have the 1:1 face verification code and can you share with me thank you ?

ypw-lbj commented 4 years ago

请问您使用预训练模型了吗？ Have you used the pre training model?