{{ message }}
This repository was archived by the owner on Jul 7, 2023. It is now read-only.
Adding extra linear to semantic hashing discretization bottleneck.#1578
Merged
Merged
Conversation
Contributor
Author
|
I signed it! |
|
CLAs look good, thanks! ℹ️ Googlers: Go here for more info. |
Contributor
|
Hey @martiansideofthemoon -- thanks so much for the fix, I'll merge this in shortly, but would it be easy to add a unit test too to check if the fix works? |
Contributor
Author
|
Hi @afrozenator, what kind of a unit test would be useful? Should I compare the shapes of the input / output? |
Contributor
|
Thanks a lot again for doing this @martiansideofthemoon ! Merging this now. |
Contributor
tensorflow-copybara
pushed a commit
that referenced
this pull request
Jun 7, 2019
PiperOrigin-RevId: 252137294
This file contains hidden or 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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.

This fixes the semantic hashing bug mentioned here https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/models/research/transformer_vae.py#L870
@dustinvtran, @lukaszkaiser is this the correct way to fix this bug?