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

TypeError: add_param_group() missing 1 required positional argument: 'param_group' #225

Open
langineer opened this issue Sep 29, 2023 · 0 comments

Comments

@langineer
Copy link

langineer commented Sep 29, 2023

trying to run training for the Grace model:


dataset = get_node_dataset('cora')
dataloader = DataLoader(dataset[0])
encoder = Encoder(feat_dim=dataset[0].x.shape[1], hidden_dim=embed_dim, n_layers=2, gnn='gcn', node_level=True, graph_level=False)
grace = GRACE(dim=embed_dim, dropE_rate_1=0.2, dropE_rate_2=0.4, maskN_rate_1=0.3, maskN_rate_2=0.4, tau=0.4, device=0)
grace.train(encoders=encoder, data_loader= dataloader,epochs=10, per_epoch_out=False, optimizer = torch.optim.Adam)

getting an error from contrastive.py:
optimizer.add_param_group({"params": self.proj_head_n.parameters()})

TypeError: add_param_group() missing 1 required positional argument: 'param_group'

any pointers?

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

No branches or pull requests

1 participant