Allow for covariant normalization in metatensor.learn.nn.EquiLayerNorm
#567
Labels
Learn
Related to metatensor-learn in Python
metatensor.learn.nn.EquiLayerNorm
#567
PR #513 is soon to be merged, which implements
EquiLayerNorm
as ametatensor-learn.nn
building block. This maintains equivariance when applying a transformation to a TensorMap by only applying aLayerNorm()
to the invariant blocks. For the covariants, anIdentity()
layer is applied. However, in principle normalisations can be applied to covariants iff they maintain covariance.Opening this issue as feature request - extend the current
EquiLayerNorm
to allow for covariant normalization beyond just applying the Identity operation.The text was updated successfully, but these errors were encountered: