It's different with the standard SegNet about piwise HOT 9 OPEN

from piwise.

yes, i'd like to do that. i have rewrited segnet.i will send it by my pull.

from piwise.

    self.dec1 = features[0: 4]    #[0,3]
    self.dec2 = features[5: 9]    #[5,8]
    self.dec3 = features[10: 16]  #[10,15]
    self.dec4 = features[17: 23]  #[17,22]
    self.dec5 = features[24: -1]  #[24,29]

while there's also a maxpool2d layer after each decoder block in the forward function, I wonder why the pooling operation is implemented twice before unpooling? I haven't run the code just quite confused.

from piwise.

@Viarow I guess this is a mistake then. Would you mind trying the correct version?

from piwise.

I'm actually a novice at deep learning, still trying to understand the codes. I guess it will work right only if the range of pretrained layers are set correct (as shown in the annotations above). I will tell you the results after I try the corrections.

from piwise.

Hi,there just one pooling at each dec. could you tell me the your found on detail.

from piwise.

from piwise.

layer4 is maxpool, it is used later in code in order to get max-index.

from piwise.

Oh I see the point. in the FCN8 model,
self.feats = nn.Sequential(*feats[0:9])
self.feat3 = nn.Sequential(*feats[10:16])
self.feat4 = nn.Sequential(*feats[17:23])
self.feat5 = nn.Sequential(*feats[24:30])
are called later in
feats = self.feats(x)
feat3 = self.feat3(feats)
feat4 = self.feat4(feat3)
feat5 = self.feat5(feat4)
fconn = self.fconn(feat5)
which means that some maxpooling layers are also left out in this model?

from piwise.