Skip to content

FPA模块中的Global Pooling那个分支最后是否有upsample #9

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

Open
wjy66 opened this issue Sep 19, 2019 · 1 comment
Open

FPA模块中的Global Pooling那个分支最后是否有upsample #9

wjy66 opened this issue Sep 19, 2019 · 1 comment

Comments

@wjy66
Copy link

wjy66 commented Sep 19, 2019

请问,FPA模块中的Global Pooling那个分支最后是否有upsample。论文的Figure3(b)中是有upsample这一模块的,而作者您的实现是直接将1x1的结果加入到最后的预测结果中。我想知道到底这个全局池化的结果是直接加还是要上采样至原图大小再与预测结果相加。谢谢~

@JaveyWang
Copy link
Owner

请问,FPA模块中的Global Pooling那个分支最后是否有upsample。论文的Figure3(b)中是有upsample这一模块的,而作者您的实现是直接将1x1的结果加入到最后的预测结果中。我想知道到底这个全局池化的结果是直接加还是要上采样至原图大小再与预测结果相加。谢谢~

没记错的话,1*1的结果出来是向量,跟特征图直接相加的话会自动广播至同样大小,所以就是已经上采样的了。

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