search

JierunChen / FasterNet

[CVPR 2023] Code for PConv and FasterNet
691 stars 55 forks source link

why not use activation functions after downsampling convolutions？ #33

Open 1920230345 opened 1 year ago

1920230345 commented 1 year ago

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

JierunChen commented 1 year ago

@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.