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

Swin #31

Open
wfz666 opened this issue Dec 1, 2024 · 2 comments
Open

Swin #31

wfz666 opened this issue Dec 1, 2024 · 2 comments

Comments

@wfz666
Copy link

wfz666 commented Dec 1, 2024

你好,我想请问论文中设置一个block中stl数量为5,是否意味着3个win,和2个swin,直觉上感觉这样不对。请问为什么不设置为6?谢谢!
Hello, I would like to ask if the number of stl in a block is set to 5 in the paper, does it mean 3 wins and 2 swins? I feel this is not right intuitively. Why not set it to 6? Thank you!

@ming053l
Copy link
Owner

ming053l commented Dec 2, 2024 via email

@ming053l ming053l closed this as completed Dec 4, 2024
@ming053l
Copy link
Owner

您好,根據我們的一些實驗結果,如果將第五個STL移除之後,參數量會進一步下降 (14M->10M)

同時伴隨一些performance drop,一方面也源於參數量降低不少,

但跟其他方法比起來,這個參數量能有這效果也算不錯的了,這些分數供您參考

DRCT-M在imagenet上預訓練的時候在Set5/Set14上約可以到32.76/29.01左右

而移除掉第五個STL的是在32.68/28.86

Hello, according to some of our experimental results, if the fifth STL is removed, the parameter-size will further decrease (14M->10M)

At the same time, it is accompanied by some performance drops. On the one hand, it is also due to the reduction in the number of parameters.

But compared with other methods, it is quite good to achieve this effect with this parameter amount. These scores are for your reference.

When DRCT-M is pre-trained on imagenet, it can reach about 32.76/29.01 on Set5/Set14.

The fifth STL was removed at 32.68/28.86

@ming053l ming053l reopened this Dec 11, 2024
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