position of batch norm layer

Hi, Guys, recently I read this book Deep Learning and Scientific Computing with R torch - 18  Image classification, take two: Improving performance.

I noticed that in the example code, some batch norm layers are after activation, some are before activation layer

is anybody who know why, I'm new to deep learning, thanks a lot

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.