We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
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?
integral
LD/mmdet/models/dense_heads/ld_head.py
Line 200 in 2dda5c0
The text was updated successfully, but these errors were encountered:
target 被缩放过了,stride就是用来做这个的
LD/mmdet/models/dense_heads/gfl_head.py
Line 246 in 2dda5c0
Sorry, something went wrong.
No branches or pull requests
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?LD/mmdet/models/dense_heads/ld_head.py
Line 200 in 2dda5c0
The text was updated successfully, but these errors were encountered: