[Gold-Yolo]inject module

[lkikinn]

Why is the Inject Module divided into two parts?

[lose4578]

This is the result of the precision-speed trade-off.

[lkikinn]

I understand that some people say that the act part can be seen as attention weight, and the whole can be seen as a process of a simple attention mechanism, like a * w + b.I don't know if that's right。

[lose4578]

Yes, the implementation of inject is a variant of attention, and of course the specific operators used to implement inject can be changed according to the actual situation, without being limited to the attention structure