Skip to content

Implemented the GIN architecture for potential use in the motion planning project#1

Open
ShreyasMuthusamy wants to merge 1 commit into
Damowerko:mainfrom
ShreyasMuthusamy:gin
Open

Implemented the GIN architecture for potential use in the motion planning project#1
ShreyasMuthusamy wants to merge 1 commit into
Damowerko:mainfrom
ShreyasMuthusamy:gin

Conversation

@ShreyasMuthusamy

Copy link
Copy Markdown
Contributor

No description provided.

Comment thread src/torchcps/gnn.py
n_taps: int,
n_layers: int = 2,
n_channels: int = 32,
architecture: str = "gcn",

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

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

Why is this being changed?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

I think that's an artifact of when I was originally going to implement the GIN architecture within the GCN class before I realized that it would be better to just implement the GIN as a separate class, so I think it's safe to delete.

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