search

yangze0930 / NTS-Net

This is a PyTorch implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification" (Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang).
MIT License
452 stars 118 forks source link

dropout in resnet.py #14

Open uniquezhengjie opened 5 years ago

uniquezhengjie commented 5 years ago

thinks for your great work, I found a err in resnet.py #line 148

x = nn.Dropout(p=0.5)(x)

set net.eval() doesn't work for it ,i think need to defind a self.drop with nn.Dropout(p=0.5) in init function or change to F.dropout(x,p=0.5,training=self.training)

paramansh commented 5 years ago

I am facing the same issue. @uniquezhengjie does your solution work?

DiKorsch commented 4 years ago

This should be fixed since the model returns at test time different results! Took me an hour to figure it out. Should have checked the issues before :-/