questions about the model you built

[michaelHaha]

Hi, I am also from Beihang University. I am currently a junior student and also try to reproduce this paper.

However, I have some doubts about the model you built. It seems that the model you built is MT model. And the third convolution layer is devised to learn to perform 'subtraction' operation with outputs of two-channel convolution below.

However, in your code, it seems that you just subtract the outputs of the two-channel convolution manually and then do convolution on this subtraction.
local merge = nn.Sequential(); merge:add(nn.CSubTable()); merge:add(nn.Abs())
I suppose there is something wrong here. What do you think?

[fucusy]

What do you mean "learn to perform 'subtraction' operation"?

[michaelHaha]

I mean this,

I think it means that you cannot subtract the outputs of two columns directly.

[fucusy]

I see. you are right. Hopefully, you can add your implementation based mine and create a pull request.

[michaelHaha]

Ok, I will.