MolecularDiffusion.modules.models.oareactdiff.normalizer¶
Feature normalisation for OA-ReactDiff.
Ported verbatim from oa_reactdiff/diffusion/_normalizer.py
(commit 543aaa8, MIT).
FEATURE_MAPPING is load-bearing beyond normalisation: it also fixes the
column order of the flat xh tensor every part of this package speaks
in – [pos (3) | one_hot (5) | charge (1)] = 9 columns, which is the
node_nfs: [9, 9, 9] in the task config.
The released checkpoint was trained with norm_values=(1,1,1) and
norm_biases=(0,0,0), i.e. no normalisation at all; the class is kept
because the diffusion loss divides by norm_values in several places and
would need those branches anyway.
Attributes¶
Classes¶
Module Contents¶
- class MolecularDiffusion.modules.models.oareactdiff.normalizer.Normalizer(norm_values: Tuple = (1.0, 1.0, 1.0), norm_biases: Tuple = (0.0, 0.0, 0.0), pos_dim: int = 3)¶
Bases:
torch.nn.Module- normalize(representations: List[Dict]) List[Dict]¶
- unnormalize(x: torch.Tensor, ind: int) torch.Tensor¶
- unnormalize_z(z_combined: List[torch.Tensor]) List[torch.Tensor]¶
- norm_biases = (0.0, 0.0, 0.0)¶
- norm_values = (1.0, 1.0, 1.0)¶
- pos_dim = 3¶
- MolecularDiffusion.modules.models.oareactdiff.normalizer.FEATURE_MAPPING = ['pos', 'one_hot', 'charge']¶