search

YuanXue1993 / SegAN

SegAN: Semantic Segmentation with Adversarial Learning
MIT License
182 stars 58 forks source link

Why the discriminator output multiplies 2 and 4？ #13

Open yuan-001 opened 4 years ago

yuan-001 commented 4 years ago 
        output = torch.cat((input.view(batchsize,-1),1*out1.view(batchsize,-1),
                            2*out2.view(batchsize,-1),2*out3.view(batchsize,-1),
                            2*out4.view(batchsize,-1),2*out5.view(batchsize,-1),
                            4*out6.view(batchsize,-1)),1)

What's the use of multiplying 2 out and 4 out6? Thank you