Skip to content
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.

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

Permutation in analytical score #113

Merged
merged 24 commits into from
Jan 8, 2025
Merged
Changes from 1 commit
Commits
Show all changes
24 commits
Select commit Hold shift + click to select a range
439d7d8
Compute log wrapped gaussians.
rousseab Dec 24, 2024
12d7871
Permutation over atomic indices.
rousseab Dec 24, 2024
83e99b8
Code a trivial factorial function to avoid importing something else.
rousseab Dec 24, 2024
58c3734
Improved analytical score network.
rousseab Dec 24, 2024
ecfe3ce
Refactor name of datamodule module.
rousseab Dec 24, 2024
b1f7255
Rename lammps preprocessor code.
rousseab Dec 24, 2024
51a612c
Better name.
rousseab Dec 24, 2024
7f10189
Align test name.
rousseab Dec 24, 2024
d6fc645
Better naming and clean data module instantiation.
rousseab Dec 24, 2024
14825ca
A new data module for on-the-fly Gaussian datasets.
rousseab Dec 24, 2024
8d54ef4
The ability to instantiate a Gaussian data module.
rousseab Dec 25, 2024
bfb8506
Make it easier to instantiate the analytical score network from a con…
rousseab Dec 25, 2024
99bbaf4
Add analytical score network to possible models to instantiate.
rousseab Dec 25, 2024
778b4d9
Fix exp details.
rousseab Dec 25, 2024
27c566a
Cleaner data module instantiation.
rousseab Dec 25, 2024
714b583
More comments for debug server.
rousseab Dec 25, 2024
bb7e1f3
Make it possible to turn off the optimizer.
rousseab Dec 25, 2024
89fb2ad
Class to plot the scores along a direction.
rousseab Dec 25, 2024
9da231e
Fancier score viewer.
rousseab Dec 26, 2024
d0d0b23
Bring scores back to cpu.
rousseab Dec 26, 2024
f335322
New callback to show scores along a path.
rousseab Dec 26, 2024
4071d3a
Fix assert error comment.
rousseab Dec 26, 2024
98afd87
Ensure that the EGNN score network works in 1D, 2D and 3D.
rousseab Dec 26, 2024
fd25a21
an example using the on-the-fly data module
rousseab Dec 27, 2024
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
Prev Previous commit
Next Next commit
The ability to instantiate a Gaussian data module.
rousseab committed Dec 25, 2024
commit 8d54ef4c5a7d08b7f60c3b736de469496d8217c3
Original file line number Diff line number Diff line change
@@ -5,6 +5,8 @@

import pytorch_lightning as pl

from diffusion_for_multi_scale_molecular_dynamics.data.diffusion.gaussian_data_module import (
GaussianDataModule, GaussianDataModuleParameters)
from diffusion_for_multi_scale_molecular_dynamics.data.diffusion.lammps_for_diffusion_data_module import (
LammpsDataModuleParameters, LammpsForDiffusionDataModule)

@@ -41,6 +43,10 @@ def load_data_module(hyper_params: Dict[AnyStr, Any], args: argparse.Namespace)
lammps_run_dir=args.data,
processed_dataset_dir=args.processed_datadir,
working_cache_dir=args.dataset_working_dir)

case "gaussian":
data_params = GaussianDataModuleParameters(**data_config, elements=hyper_params["elements"])
data_module = GaussianDataModule(data_params)
case _:
raise NotImplementedError(
f"Data source '{data_source}' is not implemented"