AllScAIP and UMA integration#496
Open
allaffa wants to merge 4 commits into
Open
Conversation
- Vendor minimal AllScAIP code under hydragnn/utils/model/allscaip/
(plus shared EScAIP utilities under hydragnn/utils/model/escaip/utils/).
- Add hydragnn/models/AllScAIPStack.py wrapper:
* runs the full transformer backbone in _embedding(), exposes the
result as the invariant node feature for HydraGNN's standard
multi-head decoders;
* uses standard num_conv_layers as the AllScAIP depth and replaces
Base's per-layer loop with a single Identity no-op iteration;
* inherits HydraGNN's activation_function (no separate
allscaip_activation knob);
* documents that AllScAIP is NOT e3nn-equivariant (scalar
transformer; SH used as input features only).
- Wire allscaip_* hyperparameters as first-class Architecture keys via
create_model / create_model_config / update_config (matches PNA,
MACE, EGNN, ... patterns).
- setup.py: switch to find_namespace_packages so the vendored
subpackages are installed.
- CI: add 'AllScAIP' to the basic mpnn parametrization in
tests/test_graphs.py::pytest_train_model and
tests/test_graphs_graphattr.py::pytest_train_model_graphattr
(8 new cases pass). Excluded from equivariant / lengths /
vectoroutput / global-attention families since AllScAIP is
is_edge_model=False and not equivariant.
- Add UMAStack thin wrapper around fairchem.core eSCNMDBackbone, with lazy import + clear error if fairchem-core is missing. - Wire uma_* config keys through create_model and update_config (sphere_channels<-hidden_dim, lmax<-max_ell, etc.); uma_hidden_channels defaults to hidden_dim. Clamp uma_mmax<=max_ell to avoid zero-channel SO(2) convs. Robust cell/pbc handling for batched PyG graphs. - Add fairchem-core to requirements-optional.txt. - Add UMA to CI parametrization in tests/test_graphs.py and tests/test_graphs_graphattr.py (basic + equivariant suites). - Add UMA to LennardJones training CI in tests/test_forces_equivariant_training.py and to the energy-only equivariance benchmark in tests/test_forces_equivariant.py. - Apply black==21.5b1 formatting.
Adds the standard 10-line BSD-3-clause header to every Python file that lacked one. The year reflects the file's last git-commit year (falls back to mtime). Vendored FairChem trees under examples/*/fairchem/core/** are intentionally skipped; they retain Meta's MIT header.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.