Reproduce the problem using fusion scheme of concatenation

[vuhoangminh]

Hi Cadene,

Thank you so much for sharing the codes.

I am trying to reproduce vqa problem using two basic fusion scheme element-wise sum and concatenation.

What I tried is to set
x_mm = torch.cat((x_q, x_v),0) in fusion.py for concat case compared to
x_mm = torch.mul(x_q, x_v) of MLBFusion

Am I right?

Thanks in advance.

[Remi]

Yes :)

And you should certainly change the size of the nn.Linear as well.

[vuhoangminh]

Thank you so much for your confirmation Cadene.