Add CPU trellis decoder#268
Merged
Merged
Conversation
mhucka
requested changes
Jul 7, 2026
mhucka
left a comment
Contributor
There was a problem hiding this comment.
This is not as throughout a review as it should be; this is a long PR and I'm kind of out of my depth on the technical and C++ details. Still, I did what I could. Hopefully the comments are more helpful than annoying …
Contributor
Author
Thank you @mhucka ! This is very helpful. I addressed many of the comments. |
mhucka
approved these changes
Jul 8, 2026
mhucka
left a comment
Contributor
There was a problem hiding this comment.
One last detail. Optional. Otherwise LGTM!
Contributor
Author
|
Thanks again for the review @mhucka ! |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds a
tesseract_trellisdecoder binary and library.I built this on a branch and opened a PR earlier (#230) but closed it because it grew too big and ocmplicted.
But I do need this tesseract trellis binary to live somewhere and anywhere now we should land it.
In the meantime at QEC26 I saw Leverrier's talk on the frontier decoder which is quite similar conceptually. There are some differences but anyways it is a nice idea and I look forward to comparing to the different future cost estimates in their paper.
Usage example:
I highly recommend to use future-detcost ranking mode to allow good performance at the smallest beam sizes.