gnn_citations.(py|md|ipynb) GRU code path does not work #1766
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Fixing some related issues. The combination_type "gated" should be "gru" If you set the combination_type to "gated" you get back a ValueError: "Invalid combination type: gated" from the aggregate method call Fixing that issue exposes another issue in that "layers.GRU" units must be an integer and not a list as it currently is hidden_units To resolve this I made a method to match the signature of the create_ffn and add multiple GRU layers However it complicates the example a bit... Also the use of hidden units like this doesn't work if the hidden_layer sizes are different. If you are happy with this change I can also update the ipynb and md files.
fchollet
reviewed
Feb 18, 2024
fchollet
approved these changes
Feb 19, 2024
sitamgithub-MSIT
pushed a commit
to sitamgithub-MSIT/keras-io
that referenced
this pull request
May 30, 2024
) * Update gnn_citations.py Fixing some related issues. The combination_type "gated" should be "gru" If you set the combination_type to "gated" you get back a ValueError: "Invalid combination type: gated" from the aggregate method call Fixing that issue exposes another issue in that "layers.GRU" units must be an integer and not a list as it currently is hidden_units To resolve this I made a method to match the signature of the create_ffn and add multiple GRU layers However it complicates the example a bit... Also the use of hidden units like this doesn't work if the hidden_layer sizes are different. If you are happy with this change I can also update the ipynb and md files. * Streamlining the code * Update the md and ipynb files * Removed accidental ipynb edits * Format with black to fix presubmit issue.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There is an optional GRU code path in the gnn_citations.(py|md|ipynb). However it doesn't currently work.
The combination_type "gated" should be "gru"
If you set the combination_type to "gated" you get back a ValueError:
"Invalid combination type: gated" from the aggregate method call
Fixing that issue exposes another issue in that "layers.GRU" units must be an integer and not a list as it currently is
hidden_unitsTo resolve this I made a method to match the signature of the create_ffn and add multiple GRU layers
However it complicates the example a bit...
Also the use of hidden units like this doesn't work if the hidden_layer sizes are different.
If you are happy with this change I will also update the ipynb and md files.