The correctness of the way to reduce or unify the numbers of channels of feature maps from backbone

[buaaMars]

Good work!
I fail to find the the way to unify the numbers of channels of the feature from the backbone in the paper. According to the original design of FPN, they use 1*1 convs to reduce the numbers of channels. However, I notice that you use 3*3 2d convs to handle with the inconsistent numbers of channels. I wonder whether this design is from the paper or yourselves?
Chinese translation:
感谢你们的工作！
fpn模块涉及到两个不同channel数的feature map相加的操作，这必然要求要先把这两个feature map的通道数统一。但是我在论文中找不到他们是怎么做的。传统的FPN是用1*1conv来做降维的，但是我发现你们的代码中用的是3*3conv。特此请求确认。
感谢！

[buaaMars]

Sorry, I made a mistake. What you do is as same as the original FPN.