Refactor of the attention example #243
Closed
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
minor ref for clarity minor ref removed get_loss
|
This is really cool, but I am a bit worried that the Perhaps some dedicated, detailed comments explaining the architecture could help. |
|
Yes, I was also worrying the same when I was coding it. Anyway, I think I will just make a blog post out of that producer-consumer example and I will try to add some inline comments as you suggest. So, I will close this and create a new pull request once I am done. |
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Outdated suggestions cannot be applied.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.
This pull request attempts to (i) avoid code duplication and (ii) make more explicit the difference between decoding during training and testing.
After some thoughts on how to accomplish this, I settled on python support for co-routines using generators (and their
nextand.send(arg)methods). I think this makes the code more clear and readable in terms of intentions, and also helps encouraging python literacy on co-routines.