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.

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

DeepID 的训练图片尺寸 #6

Closed
joyhuang9473 opened this issue Mar 29, 2016 · 1 comment
Closed

DeepID 的训练图片尺寸 #6

joyhuang9473 opened this issue Mar 29, 2016 · 1 comment

Comments

@joyhuang9473
Copy link

RiweiChen 你好,

在train_val.prototxt 的data layer 里有看你的训练图片尺寸为64x64,然而在[Deep Learning Face Representation from Predicting 10,000 Classes](http://www.ee.cuhk.edu.hk/~xgwang/papers/ sunWTcvpr14.pdf) (DeepID) 论文里提到港大使用的尺寸是39 × 31 或31 × 31

The input is 39 × 31 × k for rectangle patches, and 31 × 31 × k for square patches, where k = 3 for color patches and k = 1 for gray patches.

想请问会选择用不同的尺寸大小是有什么样的考量吗?

谢谢!

@RiweiChen
Copy link
Owner

你好,@joyhuang9473 其实没有严格的考量关系,只是说通常避免一个大的特征维度接到一个很小的特征维度中,只是我的个人经验而已。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants