Commit Graph

711 Commits (108ce1f5a1b1cd17beba2167b9482c08626f8dbe)
 

Author SHA1 Message Date
Robert Sachunsky 108ce1f5a1 Merge remote-tracking branch 'origin/main' into v3-api-release-foreal
(bad-ass difficult diff diffing)
Konstantin Baierer e0d38517d3
Merge pull request from qurator-spk/v3-api
port processor to core v3
vahidrezanezhad 2e3a29f66b In light mode: To determine whether a main region is a header, I adjusted the ratio to achieve better results.
Konstantin Baierer 85566c2186
Merge pull request from bertsky/v3-api
fix, merge, resolve conflicts, apply review, migrate sbb-binarize
Robert Sachunsky 1a0b9d1958
Merge pull request from bertsky/v3-api-refactor-init
refactoring of Eynollah init and model loading
vahidrezanezhad 38a2d60fa2 Confidence value for textregions and in the case of not light version is set to zero. This is done to let the pipeline go through. It will be updated to return the correct value in upcomming commits
vahidrezanezhad 6b52da227c docorating eynollah with textregion confidence score
Robert Sachunsky 559d001eef another fix to avoid frequent warnings
Robert Sachunsky dd478279a4 CLI: also --overwrite in single-image mode
Robert Sachunsky 8159e6336a fix typo (preventing log messages)
Robert Sachunsky 2919538382 minor fixes to avoid frequent warnings
Robert Sachunsky 903c87aca0 update readme (OCR-D section)
Robert Sachunsky dcf2ed5e22 run: also write out XML in single filename mode
Robert Sachunsky fe77171d45 run_single: reduce indentation
Robert Sachunsky c7dc952851 smoke-test: also test dir-in mode and overwrite
Robert Sachunsky 79003a083c CLI: ValueError instead of print+exit
Robert Sachunsky e17d34fafa factor run_single() out of run(), simplify kwargs
Robert Sachunsky 1a0a1cb00b remove session methods and redundant model loaders
Robert Sachunsky ab3da17547
Update requirements.txt
Co-authored-by: Konstantin Baierer <kba@users.noreply.github.com>
Robert Sachunsky dd51f900b9 OCR-D: init Eynollah in 'setup', re-use instance for each page via non-public API
Robert Sachunsky ffeb4a343d Eynollah: remove useless 'pcgts' attr
Robert Sachunsky 9dc33db108 CI: add binarization models to cache
Robert Sachunsky 9c769d4cc5 CI: run CLI tests, too
Robert Sachunsky 250fc02606 add tests for binarization, remove dependency on deps-test
vahidrezanezhad 91b2201b07 cnnrnn Ocr: width of input textline image can not be zero!
Robert Sachunsky 515b4023f6 sbb_binarize: fix missing reference
Robert Sachunsky 95a681aa8c add Continuous Deployment via Dockerhub and GHCR
Robert Sachunsky df3510750c
Github Actions CI: no more Docker clean or build
Robert Sachunsky 45e3ab9692
Github Actions: free space: all existing Docker images
vahidrezanezhad 4de441eaaa OCR prediction is now enabled to integrate results from both RGB and binarized images or to be performed on each individually
vahidrezanezhad b1da0a3327 In OCR, the predicted text is now drawn on the image, and the results are saved in a specified directory. This makes it easier to review the predicted output
Robert Sachunsky 31aeb9629d
Github Actions: free space more aggressively
Robert Sachunsky 7430b57b65 dockerfile: add smoke test
Robert Sachunsky f35f49376e run CLI test in TMPDIR, add ocrd-test
Robert Sachunsky ae066388ea docker: no need for g++, but install w/ 'EXTRAS=OCR'
Robert Sachunsky 722b5c6bf1 add make variable EXTRAS for optional dependencies
Robert Sachunsky c01609ff4e allow even more empty imports for optional dependencies
Robert Sachunsky 51e9bfd6d7 improve+extend dockerfile
Robert Sachunsky 09248d4829 improve+extend makefile
Robert Sachunsky 46618f4229 allow more empty imports for optional dependencies
Robert Sachunsky 4be89910a2 CLI: fix arg vs kwarg from merge
Robert Sachunsky 9d61acf173 simplify
Robert Sachunsky a1068ff2eb OCR-D: move sbb-binarize to ocrd-tool.json, update to v3
Robert Sachunsky c794d4d29f OCR-D: fix typo light_mode→light_version
Robert Sachunsky 4338259ca1 OCR-D: ensure page image gets replaced in result as well if not the original file
Robert Sachunsky 55969b0173 OCR-D: add docstring
Robert Sachunsky 3916474b8b OCR-D: require >=v3.1
Robert Sachunsky 6d02e90570 OCR-D: restrict max_workers=1
Robert Sachunsky efd3fa6775 allow empty imports for optional dependencies
Robert Sachunsky 238132e260 use 'image_filename' for pseudo-iteration outside 'dir_in' mode