Refine Net

[Tiamo666]

I guess maybe there is some problems in implementation of refine net.
In your refineNet.py, you define the forward pass as follows:
def forward(self, x):
refine_fms = []
for i in range(4):
refine_fms.append(self.cascadei)
out = torch.cat(refine_fms, dim=1)
out = self.final_predict(out)
return out
I think you should inverse the x, eg: x = x[::-1], because x[0] is the smallest feature map, and x[3] is biggest feature map. And there are 3 bottlenecks after smallest feature map , 0 bottleneck after biggest feature map according to paper.

[GengDavid]

Hi, @Tiamo666
Yes, you are right. It is suppose to have 3 bottlenecks after the smallest feature map and no bottleneck after the biggest feature map.
Thanks for pointing it out!
I'll correct it.

[Tiamo666]

Thanks a lot for your reimplementation work.

[GengDavid]

I’ve updated the codes and results, so I am going to close this issue.
If you still have any questions, feel free to reopen it.