-
Notifications
You must be signed in to change notification settings - Fork 530
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
为什么,预测出来的边框比较宽? #91
Comments
same question. I tried many fancy networks, all with "thicker" edges comparing with gt. any ideas? |
LPCB和DSCN减轻了这个问题,但是没有开源。原因包括损失函数和上采样时分辨率的丢失,我现在正在解决这个问题 |
对,我也尝试了一些方法,但是均衡了速度和效果[我这边实际场景对性能更加苛刻一些],所以使用了两阶段的方法,先检测位置,后分割
…------------------ 原始邮件 ------------------
发件人: "s9xie/hed" ***@***.***>;
发送时间: 2021年12月7日(星期二) 晚上6:40
***@***.***>;
***@***.******@***.***>;
主题: Re: [s9xie/hed] 为什么,预测出来的边框比较宽? (#91)
LPCB和DSCN减轻了这个问题,但是没有开源。原因包括损失函数和上采样时分辨率的丢失,我现在正在解决这个问题
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
Triage notifications on the go with GitHub Mobile for iOS or Android.
|
Towards improving edge quality using combinatorial optimization and a novel skeletonize algorithm |
谢谢你,这篇论文的评测指标或许对我很有帮助。我最近做了一个边缘检测模型能够很好的抑制噪声并产生大约3个像素宽的薄边缘,就是ods上不去,反应不了提升 |
您好,你是先提取出边缘,然后再用语义分割的吗? |
No description provided.
The text was updated successfully, but these errors were encountered: