Skip to content

Issues: xialuxi/arcface-caffe

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.

Sign up for GitHub

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

34 Open 15 Closed
34 Open 15 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Is it mandatory to use Nvidia GPU, can we use OpenCL instead?
#51 opened Oct 24, 2022 by rajhlinux
accuracy_hat_arc不超过0.6，损失处于1.5
#50 opened Jan 11, 2021 by shajie17
pose = pose * 90.0是出来的pose要旋转的意思吗？
#49 opened Aug 24, 2020 by xzou999
卷积层是否使用偏置 bias_term
#48 opened May 21, 2020 by wu-ruijie
训练过程精度较高，测试的时候精度确不高？
#47 opened Apr 3, 2020 by Harry-675
Optimizer
#46 opened Mar 16, 2020 by melgor
Compile on ubuntu
#45 opened Jan 4, 2020 by fehimebetul
关于adacos中的m
#44 opened Dec 10, 2019 by ZhangKangLong
1
为什么loss为87.33，accuracy为1？
#43 opened Dec 5, 2019 by changgongcheng
2
Did anyone try AdaCos?
#42 opened Nov 12, 2019 by borisgribkov
2
softmax计算
#41 opened Oct 17, 2019 by wu-ruijie
关于CosinAddmLayer和combined_margin_layer的疑问
#40 opened Sep 24, 2019 by wu-ruijie
mnist的例子
#39 opened Sep 24, 2019 by xdg2016
SV-X-Softmax的.cu文件
#36 opened Aug 1, 2019 by xisi789
The Predictions of Landmarks is not accurate at all
#34 opened Jul 17, 2019 by PhenomenalOnee
1
AdaCos的问题
#33 opened Jul 9, 2019 by stupiding
3
训练时loss损失一直不变，希望指点一下
#32 opened Jun 27, 2019 by jinpeifei2015
3
Could you share wingloss example
#31 opened Jun 17, 2019 by zys1994
15
讨论：前向计算w做了归一化，而反向传播更新w的时候，是按照归一化前来计算梯度，是否会导致收敛困难？
#29 opened Jun 5, 2019 by xialuxi
2
Could you provide the adacos_add_m_scale_layer.cu file ? thx
#28 opened May 27, 2019 by SCUT2014
1
caffe 训练速度仍然很慢，请问作者后来有发现这个问题吗，
#26 opened May 13, 2019 by shiyuanyin
14
以前和现在的 cosin_add_m scale 的实现区别是什么昵
#25 opened May 13, 2019 by shiyuanyin
2
NormL2没有找到
#24 opened May 10, 2019 by Amanda-Barbara
2
doesnot work in the two class classification model training
#23 opened Apr 26, 2019 by ailihong
landmark检测结果不对
#21 opened Apr 16, 2019 by Ghustwb
2
ProTip! Exclude everything labeled bug with -label:bug.