Skip to content

Issues: TinyZeaMays/CircleLoss

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

13 Open 22 Closed
13 Open 22 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

我想用在基于CNN的实例级图像检索中去，请问能够实现吗
#35 opened Mar 20, 2023 by huanhao15
1
What if similarity_matrix[positive_matrix] is empty?
#34 opened Jun 15, 2022 by liamsun2019
梯度图怎样画的？
#33 opened May 10, 2022 by genhao3
不收敛啊，需要PK采样么
#32 opened Apr 24, 2022 by onlinehuazai
self.soft_plus(torch.logsumexp(logit_n, dim=0) + torch.logsumexp(logit_p, dim=0))
#30 opened Jan 20, 2021 by Heath-zyl
2
能用在语义分割中吗
#29 opened Dec 17, 2020 by feivelliu
The meaning of detaching sp and sn from the gradient gragh?
#28 opened Dec 11, 2020 by WeiQiangRao
why are sp and sn both decreasing during training process?
#27 opened Sep 21, 2020 by wj1tr0y
3
AttributeError: 'Tensor' object has no attribute 'logical_not'
#24 opened Aug 27, 2020 by kevinbro96
2
circle loss 的适用范围？
#18 opened Jul 5, 2020 by Singapore-mor
2
RuntimeError: "triu" not implemented for 'Bool'
#17 opened May 23, 2020 by PR1706
8
我使用了该loss，但在行人reid任务上，最终的性能很难达到作者公布的结果，请问作者有复现出这个结果吗？
#8 opened Apr 8, 2020 by qiguming
27
和arcface这些损失函数一样，circle loss也应该是和全连接层的权重求相似度吧，convert_label_to_similarity这个函数看不懂啊
#6 opened Apr 7, 2020 by westnight
20
ProTip! Exclude everything labeled bug with -label:bug.