-
Notifications
You must be signed in to change notification settings - Fork 172
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
Accuracy on LFW #6
Comments
You can try to set |
@clcarwin I have tried that, after 5 epoch, loss came to nan, and acc will be 50% |
@yao5461 Can you give me your email? I have some questions about sphereface_pytorch. Thanks very much! |
@HaoLiuHust I meet the same problem, have you solved it? Thanks, if you can share a solution for working around. |
@YihangLou change the learning rate to a smaller number, however, I can not get the acc reported here |
thank you i solve it in the same way. the performce is still under the expectation
发自我的 iPhone
在 2018年3月2日,11:02,Liu, Hao <notifications@github.com<mailto:notifications@github.com>> 写道:
@YihangLou<https://github.com/yihanglou> change the learning rate to a smaller number, however, I can not get the acc reported here
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub<#6 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AHhbgiPtjnwM9zfW9ENg6APBrx0ilh1vks5taLZTgaJpZM4QMlGe>.
|
I train on washed casia-web-face(~450k) and test on lfw with accuracy-61%. All params was default. What can be problem? |
@yao5461 Have u got a good work when set phiflag to False? |
@yao5461 Did you train on original or cleaned Casisa-WebFace? |
@Gerkam Can u provide a valid link to download cleaned Casia-Webface washed list? |
@Gerkam I've found these websites too, however the links are all dead. Do u have other valid download link? |
@timho102003 The washed list can be downloaded from http://pan.baidu.com/s/1kUdRRJT with password 3zbb . For fast download find manuals how can you do it from baidu |
@Gerkam when entering the password, baidu shows that the content is illegal and cannot be downloaded. I don't really understand ur last sentence. Does that mean I should find a way to download such data from baidu?? |
@timho102003 After enter password I see all files. So, maybe baidu block request from your country or another reason. In previous post I mean, if you want download with good speed you must see how can you do it. By default speed will be slow. |
@clcarwin @yao5461 Is there an error in the lfw_eval code? sphereface_pytorch/lfw_eval.py Line 114 in e2f11f0
in the original paper it said the original and flipped image features are concatenated together, and then to calculate the cosine similarity. As shown here: https://github.com/wy1iu/sphereface/blob/a848797f1b1da00ef756ea73b38b4926cc3563cd/test/code/evaluation.m#L112. |
@RyanCV I have the same question. Do you think it should be changed to: f1,f2 = [f[0],f[1]], [f[2],f[3]]? |
Hi clcarwin,
I run the code: python train.py, with default hyper parameters.
and evaluate on lfw: python lfw_eval.py.
The accuracy is: LFWACC=0.9907 std=0.0033 thd=0.3250.
For your model, the accuracy is: LFWACC=0.9922 std=0.0054 thd=0.3050.
Is there any advice? What else should I do?
Thanks!
The text was updated successfully, but these errors were encountered: