search

xiaolai-sqlai / mobilenetv3

mobilenetv3 with pytorch，provide pre-train model
MIT License
1.6k stars 340 forks source link

The last two FC layers don't need batch norm. #11

Open longxianlei opened 5 years ago

longxianlei commented 5 years ago

NBN denotes no batch normalization. In the original paper. In table 1. The author use conv2d 1x1, NBN in the 1x1x960 to 1x1x1280, which means they don't use batch norm in fc layers, but your code use bn. This is not the same as the original version of the paper. Although this little change may not influence the final results.

out = self.hs3(self.bn3(self.linear3(out))) out = self.linear4(out)

xiaolai-sqlai commented 5 years ago

some details are not the same as original paper, because I do lots of experiments, so I just do as is the custom.