IntelLabs / matsciml

Open MatSci ML Toolkit is a framework for prototyping and scaling out deep learning models for materials discovery supporting widely used materials science datasets, and built on top of PyTorch Lightning, the Deep Graph Library, and PyTorch Geometric.
MIT License
144 stars 20 forks source link

Rename src/dst Nodes For Point Cloud Featurization #228

Closed melo-gonzo closed 4 months ago

melo-gonzo commented 4 months ago

Would close the issue raised in #132 and #227. Renames the src_nodes and dst_nodes that are used for point cloud featurization to pc_src_nodes and pc_dst_nodes.

laserkelvin commented 4 months ago

I'm trying to grasp the connection between renaming the variables and how it addresses #132 and #227. Could you explain how the renaming impacts this?

melo-gonzo commented 4 months ago

@laserkelvin src_nodes and dst_nodes are added to the overall data sample in the dataset classes. these same src_nodes and dst_nodes are pulled out when constructing the graph, for example in the dgl conversion . your own comment here may clear it up for you.

laserkelvin commented 4 months ago

Pre-commit hooks are failing on test_dataset, can you address them?