invariant-point-attention icon indicating copy to clipboard operation
invariant-point-attention copied to clipboard

Implementation of Invariant Point Attention, used for coordinate refinement in the structure module of Alphafold2, as a standalone Pytorch module

Results 2 invariant-point-attention issues
Sort by recently updated
recently updated
newest added

@lucidrains I would like to ask about the equivariance of the transformer (not IPA blocks). I wonder if you checked for the equivariance of the output when you allow the...

Hi, this is probably highly version-dependent (I have pytorch=1.11.0, pytorch3d=0.7.0 nightly), but I thought I'd report it. Torch doesn't like the in-place detach of the rotation tensor. Full stack trace...