Skip to content

Refactor sevennet model #172

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 24, 2025
Merged

Refactor sevennet model #172

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cb76265
fix wrong dtype compare
YutackPark Apr 23, 2025
1378049
make sure sevennet type_map exists
YutackPark Apr 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions torch_sim/models/sevennet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,12 +77,13 @@ def __init__(
neighbor_list_fn (Callable): Neighbor list function to use.
Default is vesin_nl_ts.
device (torch.device | str | None): Device to run the model on
dtype (torch.dtype | None): Data type for computation
dtype (torch.dtype): Data type for computation

Raises:
ValueError: the model doesn't have a cutoff
ValueError: the model has a modal_map but modal is not given
ValueError: the modal given is not in the modal_map
ValueError: the model doesn't have a type_map
"""
super().__init__()

Expand All @@ -92,14 +93,18 @@ def __init__(
if isinstance(self._device, str):
self._device = torch.device(self._device)

if torch.dtype is not torch.float32:
if dtype is not torch.float32:
warnings.warn(
"SevenNetModel currently only supports"
"float32, but received different dtype",
UserWarning,
stacklevel=2,
)

if not model.type_map:
raise ValueError("type_map is missing")
model.eval_type_map = torch.tensor(data=True)

self._dtype = dtype
self._memory_scales_with = "n_atoms_x_density"
self._compute_stress = True
Expand All @@ -108,9 +113,6 @@ def __init__(
if model.cutoff == 0.0:
raise ValueError("Model cutoff seems not initialized")

model.eval_type_map = torch.tensor(
data=True,
) # TODO: from sevenn not sure if needed
model.set_is_batch_data(True)
model_loaded = model
self.cutoff = torch.tensor(model.cutoff)
Expand Down