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

Mesh-Graph Network Example #2185

Open
wants to merge 5 commits into
base: develop
Choose a base branch
from
Open

Mesh-Graph Network Example #2185

wants to merge 5 commits into from

Conversation

szaman19
Copy link
Collaborator

@szaman19 szaman19 commented Feb 2, 2023

A partially completed data parallel implementation of Mesh Graph Network

Partially completed as the Normalizer operation in the original is currently unsupported, but potentially could be simply added via an external layer. It is similar to Batch Norm but with some slight changes.

Pinging: @bvanessen @tbennun @ndryden

@szaman19
Copy link
Collaborator Author

To do:

  • Add normalizer of initial input
  • Add an integration test with synthetic data

@tbennun
Copy link
Contributor

tbennun commented Feb 23, 2023

@szaman19 for normalizer you can use batchnorm afaiu

Copy link
Contributor

@tbennun tbennun left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great work! Some comments/questions remain on the model and the files need some standard formatting.

@@ -0,0 +1,114 @@
import lbann
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing header (applies to all files)

applications/graph/MeshGraphNet/README.md Outdated Show resolved Hide resolved
applications/graph/MeshGraphNet/README.md Outdated Show resolved Hide resolved
applications/graph/MeshGraphNet/README.md Show resolved Hide resolved


DATA_CONFIG = configparser.ConfigParser()
DATA_CONFIG.read("data_config.ini")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What if this file does not exist?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ended up including an example file in the example.

name=None):

super().__init__()
MLP.global_count += 1
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we have to give names to MLPs?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I usually add it for compute graph visualization and for better debugging messages when things break

(Layer): Expected shape (Batch, N, self.out_dim)
"""
self.instance += 1
name = f"{self.name}_instance_{self.instance}"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unused

class EdgeProcessor(Module):
""" Applies MLP transform on concatenated node and edge features
"""
global_count = 0
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same

applications/graph/MeshGraphNet/GNN.py Outdated Show resolved Hide resolved
applications/graph/MeshGraphNet/GNNComponents.py Outdated Show resolved Hide resolved
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants