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
Detail on softmax #4
Comments
Hi @DevinKreuzer, The graphtransformer/layers/graph_transformer_layer.py Lines 18 to 19 in 3c83b4b
graphtransformer/layers/graph_transformer_edge_layer.py Lines 44 to 48 in 3c83b4b
Hope this helps for understanding the implementation. |
Closing the issue for now. Feel free to open for any (further) clarification. |
Great work!
I have a question concerning the implementation of softmax in the graph_transformer_edge_layer.py
When you define the softmax, you use the following function:
Shouldn't the attention weights/scores be scalars? From what I see, each head has an 8-dimensional score vector which you then compute .sum() on. The graph_transformer_layer.py layer does not have this .sum() function.
Would appreciate any clarification on this :)
Best,
Devin
The text was updated successfully, but these errors were encountered: