What about deform_conv implementation? #797
JamesYang568
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
在mmdetection的
tood
等模块中使用了变形卷积deform_sampling
操作(或类似的offset操作),然而mmyolo中目前提供的模型好像没有该实现。尽管在mmyolo中可以非常方便的使用openlab家族中的任何函数和类,但我发现由于mmyolo精巧地将Head与HeadModule分开来写,bbox的decoding
位置后延,一定程度上造成了调用DeformConv2dFunction
的困难。若将offset矩阵传递到Head中,本就不大的显存空间捉襟见肘;若原地完成bbox的decoding
工作,将破坏mmyolo拆分模块的目的。基于此,请问有什么编程上的技巧可以借鉴,以最小程度地更改代码?Beta Was this translation helpful? Give feedback.
All reactions