Skip to content
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

Jump to bottom

hello！我想请教一下这个项目中使用的resnet50是tf官方的网络吧，原版insightface论文中使用的是修改后的resnet50，有对比过哪个效果更好吗？ #19

Open
FelixZhang7 opened this issue May 25, 2020 · 5 comments
Open

hello！我想请教一下这个项目中使用的resnet50是tf官方的网络吧，原版insightface论文中使用的是修改后的resnet50，有对比过哪个效果更好吗？ #19

FelixZhang7 opened this issue May 25, 2020 · 5 comments

Comments

@FelixZhang7
Copy link

No description provided.

@peteryuX
Copy link
Owner

Hi @FelixZhang7 ! Can you point out what the difference between them? I think maybe I ignored it.

@FelixZhang7
Copy link
Author

@peteryuX insightface的resnet默认会把第一个7x7的卷积换成3x3，并去掉pool操作(人脸识别输入分辨率112x112比ImageNet小)，另外当层数大于101时才使用先1x1再3x3再1x1的bottleneck结构，resnet50里面还是2个3x3卷积，还提出了一种称为IRblock对block进行改进，文章说更适合对人脸图片的训练了

@peteryuX
Copy link
Owner

Hi @FelixZhang7 , 感謝您提點我這些資訊，聽起來這些改動應該是會帶來性能上的提升。不過，我好像沒有在paper中看到相關的文字說明，請問我是不是遺漏了甚麼?

@FelixZhang7
Copy link
Author

FelixZhang7 commented May 25, 2020 •
edited
Loading

image论文里边我也找不到了。。。不过很多复现acrface的网络都叫LResnet50E-IR

@peteryuX
Copy link
Owner

@FelixZhang7 ， 還是謝謝您的提點，關於LResnet50E-IR的部分，我會嘗試實現並完善於這個項目中~ =)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@peteryuX @FelixZhang7