search

sacmehta / ESPNet

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
https://sacmehta.github.io/ESPNet/
MIT License
541 stars 112 forks source link

Would please explain why the train/test models are slightly different? #32

Closed zhengxiawu closed 5 years ago

zhengxiawu commented 5 years ago

e.g. Test:

concat_features = self.conv(torch.cat([comb_l2_l3, output0], 1))

Train:

concat_features = self.conv(torch.cat([comb_l2_l3, output0_cat], 1))

Is this will be harmful to the results?

sacmehta commented 5 years ago

see #14