about invalid syntax on code

[AhmetGG]

Hi.I am a new user of Graph neural Network. While I was looking at the code on internet I got the error message on the exam code. But I could not find where I make a mistake. How can I do this ? The error is invalid syntax for (conv1): GATConv(2, 32, heads=2)

##############################################

odel = GCN(hidden_channels=16)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
criterion = torch.nn.CrossEntropyLoss()

def train():
model.train()
optimizer.zero_grad()
out = model(data.x, data.edge_index)
loss = criterion(out[data.train_mask], data.y[data.train_mask])
loss.backward()
optimizer.step()
return loss

def test():
model.eval()
out = model(data.x, data.edge_index)
pred = out.argmax(dim=1)
test_correct = pred[data.test_mask] == data.y[data.test_mask]
test_acc = int(test_correct.sum()) / int(data.test_mask.sum())
return test_acc

for epoch in range(1, 101):
loss = train()
print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')
GAT(
(conv1): GATConv(1433, 8, heads=8)
(conv2): GATConv(64, 7, heads=8)
)
####################################

[rusty1s]

Simply removing

GAT(
(conv1): GATConv(1433, 8, heads=8)
(conv2): GATConv(64, 7, heads=8)
)

from the code should resolve this. I assume this relates to console output and not meant to be part of your script.

[AhmetGG]

Thank you for your reply. I tried to extract that part before but I still get error but different. its error message is init() missing 2 required positional arguments: 'in_channels' and 'out_channels' for first line. where can I focus on for channel?

[rusty1s]

Try initializing the model via in_channels=dataset.num_features and out_channels=dataset.num_classes.