About the calculation of the distance matrix in class "NNMatcher"

[WallofWonder]

I understand that variables d1 and d2 are the sum of squares of each descriptor But I don't know why the distance matrix in NNMatcher.run is calculated like this

d1, d2 = (desc1**2).sum(1), (desc2**2).sum(1)
distmat = (d1.unsqueeze(1) + d2.unsqueeze(0) - 2*torch.matmul(desc1, desc2.transpose(0,1))).sqrt()

Especially the part - 2*torch.matmul(desc1, desc2.transpose(0,1)) is confusing me

Anybody knows how it works?