Added basic tree BPE implementation.#152
Open
AMS-Hippo wants to merge 2 commits into
Open
Conversation
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Edited the BPE implementation from STAMP to match the input/output of other tree/compression methods in the library.
I don't include the example notebook in this push, because it doesn't seem very important. I'll add it to my own fork soon, so it will be accessible if we decide we want it.
I tested the STAMP version quite a bit. I tested this rewrite less, since the basic algorithm is the same. It seems to do OK on small examples, and overall run-time was similar (roughly ~2 seconds to do ~30 contractions on a million nodes for my computer). There is a lot of room for acceleration if we decide to use this for larger examples, and especially for very large numebrs of contractions.