How to calculate the relative positional embeddings from a row offset and column offset? about stand-alone-self-attention HOT 3 OPEN

Thanks for your comments !
The paper is implemented referring to the following paper.

Attention Augmented Convolutional Networks Link

Thank you.

from stand-alone-self-attention.

@leaderj1001
Hello, I wonder whether you implement the relative position embedding in the selfattention.
I notice that you just exploit two random tensors to represent position in h and w direction while the paper said "The row and column offsets are associated with an embedding r_{a−i} and r_{b−j}".
I am confused about whether the so called "embedding" should be implemented as the nn.Embedding operation in pytorch.

from stand-alone-self-attention.

@leaderj1001
Hello, I wonder whether you implement the relative position embedding in the selfattention.
I notice that you just exploit two random tensors to represent position in h and w direction while the paper said "The row and column offsets are associated with an embedding r_{a−i} and r_{b−j}".
I am confused about whether the so called "embedding" should be implemented as the nn.Embedding operation in pytorch.

Hi, I am having the same question here. Did you figure out how to compute the relative position embedding？Thanks

from stand-alone-self-attention.