Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ORNL/HydraGNN
Distributed PyTorch implementation of multi-headed graph convolutional neural networks
https://github.com/ORNL/HydraGNN
machine-learning
Last synced: 2 months ago
JSON representation
Distributed PyTorch implementation of multi-headed graph convolutional neural networks
- Host: GitHub
- URL: https://github.com/ORNL/HydraGNN
- Owner: ORNL
- License: bsd-3-clause
- Created: 2021-05-28T03:32:03.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2024-10-29T18:15:36.000Z (2 months ago)
- Last Synced: 2024-10-29T20:23:06.536Z (2 months ago)
- Topics: machine-learning
- Language: Python
- Homepage:
- Size: 7.82 MB
- Stars: 65
- Watchers: 10
- Forks: 28
- Open Issues: 25
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
- best-of-atomistic-machine-learning - GitHub - 34% open · ⏱️ 31.12.2024): (Representation Learning)
README
# HydraGNN
Distributed PyTorch implementation of multi-headed graph convolutional neural networks
## Dependencies
To install required packages with only basic capability (`torch`,
`torch_geometric`, and related packages)
and to serialize+store the processed data for later sessions (`pickle5`):
```
pip install -r requirements.txt
pip install -r requirements-torch.txt
pip install -r requirements-pyg.txt
```
If you plan to modify the code, include packages for formatting (`black`) and
testing (`pytest`) the code:
```
pip install -r requirements-dev.txt
```
Detailed dependency installation instructions are available on the
[Wiki](https://github.com/ORNL/HydraGNN/wiki/Install)
## Installation
After checking out HydgraGNN, we recommend to install HydraGNN in a
developer mode so that you can use the files in your current location
and update them if needed:
```
python -m pip install -e .
```
Or, simply type the following in the HydraGNN directory:
```
export PYTHONPATH=$PWD:$PYTHONPATH
```
Alternatively, if you have no plane to update, you can install
HydraGNN in your python tree as a static package:
```
python setup.py install
```
## Running the code
There are two main options for running the code; both require a JSON input file
for configurable options.
1. Training a model, including continuing from a previously trained model using
configuration options:
```
import hydragnn
hydragnn.run_training("examples/configuration.json")
```
2. Making predictions from a previously trained model:
```
import hydragnn
hydragnn.run_prediction("examples/configuration.json", model)
```
### Datasets
Built in examples are provided for testing purposes only. One source of data to
create HydraGNN surrogate predictions is DFT output on the OLCF Constellation:
https://doi.ccs.ornl.gov/
Detailed instructions are available on the
[Wiki](https://github.com/ORNL/HydraGNN/wiki/Datasets)
### Configurable settings
HydraGNN uses a JSON configuration file (examples in `examples/`):
There are many options for HydraGNN; the dataset and model type are particularly
important:
- `["Verbosity"]["level"]`: `0`, `1`, `2`, `3`, `4`
- `["Dataset"]["name"]`: `CuAu_32atoms`, `FePt_32atoms`, `FeSi_1024atoms`
- `["NeuralNetwork"]["Architecture"]["model_type"]`: `PNA`, `MFC`, `GIN`, `GAT`, `CGCNN`, `SchNet`, `DimeNet`, `EGNN`
### Citations
"HydraGNN: Distributed PyTorch implementation of multi-headed graph convolutional neural networks", Copyright ID#: 81929619
https://doi.org/10.11578/dc.20211019.2
## Contributing
We encourage you to contribute to HydraGNN! Please check the
[guidelines](CONTRIBUTING.md) on how to do so.