Robert Sachunsky
|
a41f18b13d
|
CI: (try to) store/upload coverage results
|
2 months ago |
|
Robert Sachunsky
|
4339444e47
|
binarization CLI: fix option checks, simplify to asserts, fix dir_in mode
|
2 months ago |
|
Robert Sachunsky
|
56cc179d35
|
pytest: add tests for directory mode (layout+bin)
|
2 months ago |
|
Robert Sachunsky
|
a3e1b3d4d5
|
pytest: add asserts for results, add binarization
|
2 months ago |
|
Robert Sachunsky
|
b03116f4a6
|
pytest: use subtests for various layout options, add coverage
|
2 months ago |
|
Robert Sachunsky
|
91a340f619
|
CLI: simplify option checks to asserts (also avoid stack trace)
|
2 months ago |
|
Robert Sachunsky
|
e0a7fde537
|
logger: fix type hint
|
2 months ago |
|
Robert Sachunsky
|
108ce1f5a1
|
Merge remote-tracking branch 'origin/main' into v3-api-release-foreal
(bad-ass difficult diff diffing)
|
2 months ago |
Konstantin Baierer
|
e0d38517d3
|
Merge pull request #130 from qurator-spk/v3-api
port processor to core v3
|
2 months ago |
vahidrezanezhad
|
2e3a29f66b
|
In light mode: To determine whether a main region is a header, I adjusted the ratio to achieve better results.
|
2 months ago |
|
Konstantin Baierer
|
85566c2186
|
Merge pull request #148 from bertsky/v3-api
fix, merge, resolve conflicts, apply review, migrate sbb-binarize
|
2 months ago |
Robert Sachunsky
|
1a0b9d1958
|
Merge pull request #1 from bertsky/v3-api-refactor-init
refactoring of Eynollah init and model loading
|
2 months ago |
|
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
|
2 months ago |
|
vahidrezanezhad
|
6b52da227c
|
docorating eynollah with textregion confidence score #135
|
2 months ago |
|
Robert Sachunsky
|
559d001eef
|
another fix to avoid frequent warnings
|
2 months ago |
|
Robert Sachunsky
|
dd478279a4
|
CLI: also --overwrite in single-image mode
|
2 months ago |
|
Robert Sachunsky
|
8159e6336a
|
fix typo (preventing log messages)
|
2 months ago |
|
Robert Sachunsky
|
2919538382
|
minor fixes to avoid frequent warnings
|
2 months ago |
|
Robert Sachunsky
|
903c87aca0
|
update readme (OCR-D section)
|
2 months ago |
|
Robert Sachunsky
|
dcf2ed5e22
|
run: also write out XML in single filename mode
|
2 months ago |
|
Robert Sachunsky
|
fe77171d45
|
run_single: reduce indentation
|
2 months ago |
|
Robert Sachunsky
|
c7dc952851
|
smoke-test: also test dir-in mode and overwrite
|
2 months ago |
|
Robert Sachunsky
|
79003a083c
|
CLI: ValueError instead of print+exit
|
2 months ago |
|
Robert Sachunsky
|
e17d34fafa
|
factor run_single() out of run(), simplify kwargs
|
2 months ago |
|
Robert Sachunsky
|
1a0a1cb00b
|
remove session methods and redundant model loaders
|
2 months ago |
|
Robert Sachunsky
|
ab3da17547
|
Update requirements.txt
Co-authored-by: Konstantin Baierer <kba@users.noreply.github.com>
|
2 months ago |
|
Robert Sachunsky
|
dd51f900b9
|
OCR-D: init Eynollah in 'setup', re-use instance for each page via non-public API
|
2 months ago |
|
Robert Sachunsky
|
ffeb4a343d
|
Eynollah: remove useless 'pcgts' attr
|
2 months ago |
|
Robert Sachunsky
|
9dc33db108
|
CI: add binarization models to cache
|
2 months ago |
|
Robert Sachunsky
|
9c769d4cc5
|
CI: run CLI tests, too
|
2 months ago |
|
Robert Sachunsky
|
250fc02606
|
add tests for binarization, remove dependency on deps-test
|
2 months ago |
|
vahidrezanezhad
|
91b2201b07
|
cnnrnn Ocr: width of input textline image can not be zero!
|
2 months ago |
|
Robert Sachunsky
|
515b4023f6
|
sbb_binarize: fix missing reference
|
2 months ago |
|
Robert Sachunsky
|
95a681aa8c
|
add Continuous Deployment via Dockerhub and GHCR
|
2 months ago |
|
Robert Sachunsky
|
df3510750c
|
Github Actions CI: no more Docker clean or build
|
2 months ago |
|
Robert Sachunsky
|
45e3ab9692
|
Github Actions: free space: all existing Docker images
|
2 months ago |
|
vahidrezanezhad
|
4de441eaaa
|
OCR prediction is now enabled to integrate results from both RGB and binarized images or to be performed on each individually
|
2 months ago |
|
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
|
2 months ago |
|
Robert Sachunsky
|
31aeb9629d
|
Github Actions: free space more aggressively
|
2 months ago |
|
Robert Sachunsky
|
7430b57b65
|
dockerfile: add smoke test
|
2 months ago |
|
Robert Sachunsky
|
f35f49376e
|
run CLI test in TMPDIR, add ocrd-test
|
2 months ago |
|
Robert Sachunsky
|
ae066388ea
|
docker: no need for g++, but install w/ 'EXTRAS=OCR'
|
2 months ago |
|
Robert Sachunsky
|
722b5c6bf1
|
add make variable EXTRAS for optional dependencies
|
2 months ago |
|
Robert Sachunsky
|
c01609ff4e
|
allow even more empty imports for optional dependencies
|
2 months ago |
|
Robert Sachunsky
|
51e9bfd6d7
|
improve+extend dockerfile
|
2 months ago |
|
Robert Sachunsky
|
09248d4829
|
improve+extend makefile
|
2 months ago |
|
Robert Sachunsky
|
46618f4229
|
allow more empty imports for optional dependencies
|
2 months ago |
|
Robert Sachunsky
|
4be89910a2
|
CLI: fix arg vs kwarg from merge
|
2 months ago |
|
Robert Sachunsky
|
9d61acf173
|
simplify
|
2 months ago |
|
Robert Sachunsky
|
a1068ff2eb
|
OCR-D: move sbb-binarize to ocrd-tool.json, update to v3
|
2 months ago |