-
Notifications
You must be signed in to change notification settings - Fork 4.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Pre-trained models (20170512-110547) VS Pre-trained models (20180402-114759) #948
Comments
I also want to know the difference between these two models |
@tensorflowt @yuwgle Can you share the drive link to the pre trained model? |
Hello! Also noticed great accuracy drop with
And I got the following results:
It seems to me that 512D embeddings contains some less informative features, which are neglected, and even help if you use SVM for face verification, but adds a lot of 'noise' if you try to compute cosine/euclidean distance between two embeddings. |
@NightFury10497 I just download the pretrained model in README.md. |
@yuwgle @tensorflowt Older version is 128 dimensional face embedding, and the new one is 512 dimensional face embedding. That's what I think these days. |
@yuwgle @tensorflowt @chenyuqing The FIXED_STANDARDIZATION is very simple as below, one can see facenet.create_input_pipeline() for details: |
20180402-114759 is for SVM embedding compare,20170512-110547 is for Euclidean/Cosine distance embedding compare, is it? |
model of 2017 mainly trained on CASIA-webface, while model of 2018 trained both on CASIA and vggface? |
Hello, David! First of all, thank you very much for sharing the pre-training model, which is very helpful to my learning.I just tested your new version of pre-training model (20180402-114759), but to my surprise, the effect is very poor. It doesn't work as well as the older version (20170512-110547).Can you help me?
Thanks!
The text was updated successfully, but these errors were encountered: