Commit Graph

51 Commits

Author SHA1 Message Date
Vik Paruchuri
1a3e135182 Integrate texify model 2025-01-27 10:47:27 -05:00
Vik Paruchuri
3278e520db Refactor scripts 2025-01-16 09:58:25 -05:00
Vik Paruchuri
7174903d54 Expand table boxes slightly 2025-01-10 09:10:23 -05:00
Vik Paruchuri
bf2f693daa Additional cleanup 2025-01-08 12:10:32 -05:00
Vik Paruchuri
d17281ea1a Refactor schema 2025-01-07 09:52:42 -05:00
Vik Paruchuri
85301313fe Refactor table rec 2025-01-06 21:58:35 -05:00
Vik Paruchuri
51c7c4acc6 Refactor OCR error model 2025-01-06 21:39:45 -05:00
Vik Paruchuri
d7f1567346 Refactor layout 2025-01-06 17:38:51 -05:00
Vik Paruchuri
1de6d9193d Refactor recognition model 2025-01-06 17:19:17 -05:00
Vik Paruchuri
187fc8f2bc Refactor detection model 2025-01-06 15:08:19 -05:00
Vik Paruchuri
e048733043 Merge dev 2025-01-06 14:23:20 -05:00
Vik Paruchuri
ffd3f5f2df New layout model
Some checks failed
Integration test / build (push) Has been cancelled
2024-12-30 12:05:36 -05:00
Vik Paruchuri
20b7b62d5d Add bad OCR detection to app 2024-12-19 10:49:25 -05:00
Vik Paruchuri
f8188f41f4 Modify prediction logic
Some checks failed
Integration test / build (push) Has been cancelled
2024-12-18 14:11:38 -05:00
Vik Paruchuri
d41dd7c839 Patch issues with table rec 2024-12-12 16:40:30 -05:00
Vik Paruchuri
237592926e Start to redo table recognition 2024-12-12 15:10:15 -05:00
Vik Paruchuri
edeea3dd02 Fix bug with extension
Some checks failed
Integration test / build (push) Has been cancelled
2024-12-05 10:20:27 -05:00
Vik Paruchuri
aa1118c7f1 Remove ordering model 2024-11-12 14:14:21 -05:00
Vik Paruchuri
9e7c755ab9 Relabel 2024-11-12 11:13:49 -05:00
Vik Paruchuri
1e1141bcfc Early checkpoint 2024-11-11 14:52:17 -05:00
Moses Paul R
2ce834a2e6
clean up layout model loading and update docs 2024-11-06 20:48:05 +00:00
Vik Paruchuri
4fa6ff60d6 Refactor to move cell assignment out of library
Some checks failed
Integration test / build (push) Has been cancelled
2024-10-11 17:06:54 -04:00
Vik Paruchuri
7af11c1791 Fix error with images
Some checks failed
Integration test / build (push) Has been cancelled
2024-10-08 12:31:52 -04:00
Vik Paruchuri
2f15cb526f Final table rec changes 2024-10-08 11:31:20 -04:00
Vik Paruchuri
e4fea86b44 Fix processor inconsistency 2024-10-08 11:08:05 -04:00
Vik Paruchuri
7240d72c4b Add highres image option, automatic text detection
Some checks failed
Integration test / build (push) Has been cancelled
2024-10-07 13:13:25 -04:00
Vik Paruchuri
a07fd356ce Add highres option for PIL images 2024-10-07 11:07:28 -04:00
Vik Paruchuri
50a8589283 Add table rec benchmark
Some checks failed
Integration test / build (push) Has been cancelled
2024-10-04 16:48:38 -04:00
Vik Paruchuri
4e89fe7fe2 Output text with bboxes 2024-10-03 18:17:26 -04:00
Vik Paruchuri
7489c14c9a Mostly handle rotation 2024-10-03 16:03:23 -04:00
Vik Paruchuri
3e2b86c3cc Add table parsing script 2024-10-03 14:39:55 -04:00
Vik Paruchuri
9989a79615 Ar version
Some checks failed
Integration test / build (push) Has been cancelled
2024-09-30 19:15:39 -04:00
Vik Paruchuri
31df896bae Initial table rec ar model
Some checks failed
Integration test / build (push) Has been cancelled
2024-09-27 11:37:17 -04:00
Vik Paruchuri
ad9fbf8420 Add new table rec model 2024-09-20 15:33:48 -04:00
Vik Paruchuri
c734a2e214 New table rec method 2024-09-16 17:03:21 -04:00
Vik Paruchuri
52e3be000a Swap encoder, do language tokenization
Some checks are pending
Integration test / build (push) Waiting to run
2024-08-02 11:28:54 -07:00
Vik Paruchuri
fd12e3ef4c Update detection model 2024-07-12 06:47:23 -07:00
Vik Paruchuri
912ab76cf4 Swap out segformers
Some checks are pending
Integration test / build (push) Waiting to run
2024-07-09 15:57:01 -07:00
Vik Paruchuri
1abd2f0fb6 Finalize integration of reading order model 2024-04-22 10:06:00 -07:00
Vik Paruchuri
9968ad2386 Resort bboxes based on layout 2024-04-16 10:14:28 -07:00
Vik Paruchuri
6b03a36da9 Add reading order model 2024-04-15 16:04:01 -07:00
Vik Paruchuri
f36040ddd4 Add tests, benchmarks 2024-03-26 11:40:16 -07:00
Vik Paruchuri
d0761200a5 Improve postprocessing 2024-03-07 14:40:17 -08:00
Vik Paruchuri
4c7d3dcb8e Fix remaining recognition issues 2024-03-06 10:41:38 -08:00
Vik Paruchuri
4a273ebad4 Add confidence scores 2024-02-29 13:09:16 -08:00
Vik Paruchuri
a637e7a67c Improve layout 2024-02-27 10:08:17 -08:00
Vik Paruchuri
f9746104de Add layout model 2024-02-23 12:11:37 -08:00
Vik Paruchuri
9017508f6c Add in math rendering 2024-02-17 20:42:02 -08:00
Vik Paruchuri
9fbef16069 Refactor to use pydantic, add in sorting 2024-02-16 13:14:42 -08:00
Vik Paruchuri
e9c26ad29b Finalize README 2024-02-12 15:01:48 -08:00