pochih / FCN-pytorch

🚘 Easiest Fully Convolutional Networks
404 stars 143 forks source link

why 'cnn-relu-bn' not' cnn-bn-relu' #21

Open 14211019 opened 5 years ago

14211019 commented 5 years ago

why you use the batch normalization after the Relu opration instead of the batch normalization before the Relu opration