XiaLiPKU / EMANet

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)
https://xialipku.github.io/publication/expectation-maximization-attention-networks-for-semantic-segmentation/
GNU General Public License v3.0
680 stars 130 forks source link

is this a bug? #8

Closed whuhit closed 5 years ago

whuhit commented 5 years ago

in train.py line 134 and 135 self.net.module.ema.mu *= momentum self.net.module.ema.mu += mu * (1 - momentum)

it maybe like this self.net.module.emau.mu *= momentum self.net.module.emau.mu += mu * (1 - momentum)

XiaLiPKU commented 5 years ago

Yes... Thank you very much!