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

关于回归的变量离散化选择 #50

Open
botaoye opened this issue Sep 18, 2022 · 1 comment
Open

关于回归的变量离散化选择 #50

botaoye opened this issue Sep 18, 2022 · 1 comment

Comments

@botaoye
Copy link

botaoye commented Sep 18, 2022

您好,感谢您的很棒的工作。我想将LD用到其他检测器中,关于把regression换成离散化的概率这部分有一个疑惑想要问问作者。我看检测器每一个scale得到的regression都通过相同的integral将概率转化成lrtb值,那么得到的lrtb都是一样的。所以最终不同feature scale的lrtb范围都是相同的,为什么不把每个scale的lrtb按照比例放缩范围呢?以及如果feature比较大,这样的实现得到的lrtb范围是否有可能小于GT lrtb的范围呢?

pos_bbox_pred_corners = self.integral(pos_bbox_pred)

@HikariTJU
Copy link
Owner

HikariTJU commented Sep 19, 2022

target 被缩放过了,stride就是用来做这个的

pos_decode_bbox_targets = pos_bbox_targets / stride[0]

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