why not use activation functions after downsampling convolutions？

Open 1920230345 opened this issue 2 years ago • 1 comments

Great work! But why not use activation functions after downsampling convolutions?

Apr 23 '23 06:04 1920230345

@1920230345 Hi, we did not conduct an ablation study on this. We suggest empirical experiments for different FasterNet variants, as further incorporating activation functions may increase or decrease the model capacity.

Apr 29 '23 00:04 JierunChen