Closed CoderPat closed 5 years ago
Can't comment on the script that generates the graph, the rest look good to me. Thanks for your help!
Note problem explained here: https://github.com/CoderPat/structured-neural-summarization/issues/4#issuecomment-482386587
Can't comment on the script that generates the graph, the rest look good to me. Thanks for your help!
Have you finished the experiment?
What I see is that TF is not happy with dealing with None tensors, so a workaround may be necessary to pass in None as labels. Passing an empty dictionary should work. This means changing the code in the OpenGNN to account for empty labels as opposed to None.
Fixes #1 ,#3, #4, #5 and #7, #12.