lucidrains / invariant-point-attention

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

lucidrains/invariant-point-attention Issues

In-place rotation detach not allowed
Closed 2 years ago1
Subtle mistake in the implementation
Closed 2 years ago1
Report a bug that causes instability in training
Closed 2 years ago1
Equivariance test for IPA Transformer
Updated 2 years ago1
Application of Invariant point attention : preserver part of structure.
Closed 2 years ago
Computing point dist - use cartesian dimension instead of hidden dimension
Closed 3 years ago3
#126 maybe omit the 'self.point_attn_logits_scale'?
Closed 3 years ago1