This repository was archived by the owner on Apr 8, 2026. It is now read-only.
Solution2 for Im2Latex problem with higher BLEU score.#34
Open
untrix wants to merge 1 commit into
Open
Conversation
untrix
changed the title
Author
|
Hello, anybody there? |
Author
|
Update: The solution has been independently verified by @dengbingfeng: please see issue #13 on our github project.
I suppose now there should be no doubt that this is a valid solution. |
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.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Thanks for putting up a list of interesting and useful problems. Am presenting a different solution to the Im2Latex problem and have achieved a BLEU score of 89% - the highest published so far. Model architecture is based on the Show, Attend and Tell paper but with significant changes in order to get to this performance level. The paper is uploaded to arXiv and a project website contains all ancillary material: datasets, visuals, results etc. (will upload tensorboard charts as well). ADAM optimizer is used to train the model. Source code is Tensorflow based and is open-sourced on github. All links are provided in this edit.
Best Regards,
Sumeet Singh