-
Notifications
You must be signed in to change notification settings - Fork 29
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ACFPN中上菜样和CxAM模块的几个问题 #3
Comments
请问作者图中的F2 F3 F4 F5是对应Resnet的后面几个stage的输出结果吧?之前在别的论文里面看标注的是C2 C3 C4 C5,所以有点不确定,希望得到你的回复!感谢! @littletomatodonkey |
是的,作者在这里是把C4->C5的dilation修改为了2(默认为1),但是我自己做实验的时候发现设置为1的话,效果会好一些。 |
您好,打扰一下。我有几个问题想请教您一下。 |
Hi, |
你好,感谢开源ACFPN,有2个问题想请教下
is_upsample
应该一直设置为True?最开始P5和C4融合时,就应该对P5进行降采样(我看backbone部分只修改了dilation,应该没有对C5的分辨率进行修改?)AC-FPN/detectron/modeling/FPN.py
Line 375 in 2e4e0b2
2.论文中的CxAM和CnAM模块中的1x1卷积部分,是否对通道数进行了缩减了呢?nonlocal中是对计算通道数减半,减少了计算量,不知道你是否有意愿开源这两个模块呢?
期待你的回复,多谢!
The text was updated successfully, but these errors were encountered: