Question about the input in "Geometric Prior"

[GongweiChen]

local-relational-nets/layer.py

Line 9 in 55eef1d

self.position = 2 * torch.rand(1, 2, k, k, requires_grad=True) - 1

Thanks for your great and elegant coding!
I have a question about "Geometric Prior". Why the inputs are random numbers, while it should be relative position in the original paper?

[hust-nj]

local-relational-nets/layer.py

Line 9 in 55eef1d

self.position = 2 * torch.rand(1, 2, k, k, requires_grad=True) - 1

Thanks for your great and elegant coding!
I have a question about "Geometric Prior". Why the inputs are random numbers, while it should be relative position in the original paper?

I found the same issue. So wired about this. Do you have any idea?

[hust-nj]

local-relational-nets/layer.py

Line 9 in 55eef1d

self.position = 2 * torch.rand(1, 2, k, k, requires_grad=True) - 1

Thanks for your great and elegant coding!
I have a question about "Geometric Prior". Why the inputs are random numbers, while it should be relative position in the original paper?

Hi, I find the paper proposes a method to learn geometric prior values denoted as LR(G*)