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

SIOU-LOSS #14

Open
szy981015 opened this issue May 29, 2022 · 6 comments
Open

SIOU-LOSS #14

szy981015 opened this issue May 29, 2022 · 6 comments

Comments

@szy981015
Copy link

你好,请问你是否使用了SIOU-LOSS作为损失函数,我看到你的README中提到了该损失函数

@jay985735639
Copy link

同问,效果上有提升吗?

@Yzg916
Copy link

Yzg916 commented Jun 7, 2022

好像运行了会报错 你们有试吗

@xialuxi
Copy link
Owner

xialuxi commented Jun 8, 2022

运行没有问题, 但是map提升体现不出来(多个数据测试过),确实有加速收敛的现象。

@williamhyin
Copy link

运行没有问题, 但是map提升体现不出来(多个数据测试过),确实有加速收敛的现象。

你好,我对你的代码中return iou - 0.5 * (distance_cost + shape_cost) 写法与论文中
image写法的不同不太理解?其次angle cost的写法也与论文中不同 angle_cost = torch.sin(torch.arcsin(sin_alpha) * 2)。请问是实践中发现论文中存在一些问题吗?

@iodncookie
Copy link

实验中,后续来贴结果

@rbchen1996
Copy link

试了好几个数据集,在较小的数据集上mAP直接降低5个百分点。

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

7 participants