There is no code files of this repo?

[yangxudong]

why this repo is empty.

[tiandunx]

I've already implemented SV-X-Softmax and it works fine!

[LaviLiu]

@tiandunx Would you like to share your code to github?

[tiandunx]

@Laviyy Sorry to reply late. Of course I'm willing to share my implementation.

[ysc703]

@tiandunx We are waiting for you! Thanks^_^

[twmht]

@tiandunx

any update?

[tiandunx]

Hi all, I'm so sorry for keeping you waiting. I shall release the code after ICCV. Sorry again. Thanks for keeping an eye upon this paper.

[luameows]

@tiandunx Would u mind tell me ur LFW accuracy? I implemented it on mnist, and the classification accuracy was not very good. As for on face recognition, the code is still running. So I cannot get the result now.

[tiandunx]

@luameows Sure, on LFW, I achieved 99.866％ using MS only.

[ysc703]

Hi all, I'm so sorry for keeping you waiting. I shall release the code after ICCV. Sorry again. Thanks for keeping an eye upon this paper.

@tiandunx After Nov 3, 2019? 😲😲😲

[tiandunx]

At the end of this month.

[wjgaas]

@tiandunx which backbone net did you use to achieve 99.866％ on lfw? res-50? or attention-56?

[twmht]

@tiandunx

What is the value of t you used? And what is the margin loss function you used?

[tiandunx]

t = 1.2, margin loss is additive margin softmax@twmht

[DevilCat]

At the end of this month.

Is the code able to be shared? I'll be very appreciated.

[tiandunx]

The code is available now.

[twmht]

@tiandunx

thanks for sharing.

So you use all the default values when set is_am=True ?

def __init__(self, feat_dim, num_class, is_am, margin=0.45, mask=1.12, scale=32):

[wjgaas]

@tiandunx Hi, which backbone net did you use to achieve 99.866％ on lfw? res-50? or attention-56?