Commit Graph

560 Commits (d9f79c3404fb6372031625d357fed5727fa6ec51)
 

Author SHA1 Message Date
vahidrezanezhad 2c93904985 avoiding double binarization
vahidrezanezhad f0b49073b7 adding option for textline detection in printspace
Clemens Neudecker c156a1612e
Exclude `run_image_extraction_over_ppn_lists.py` from merge
vahidrezanezhad 6b2e5d110e all tests are passed
vahidrezanezhad c3a4a1bba7 resolving issue in a better way
cneud b6d3d2bdbf fix indentation
cneud de32d86fb6 Merge branch 'refs/heads/main' into extracting_images_only
# Conflicts:
#	src/eynollah/eynollah.py
vahidrezanezhad 0f87974b0c writing drop capitals in xml output + and may resolve issue
Clemens Neudecker 256a7c347f
Merge pull request from qurator-spk/src-layout
Merging package src layout as agreed per meeting today.
kba 84b844203d switch from qurator namespace to src-layout
kba 9367f86483 remove setup.py stub completely
vahidrezanezhad 93005959e5 inference batch size debugged
kba 62314c453c fully transition to pyproject
kba a5c7f223d1 📦 v0.3.1
kba 9ae0575436 📝 changelog
vahidrezanezhad 7ae6a8776f ignoring dpi check by light version
vahidrezanezhad 04e79002b3 making light version faster for 1 and 2 columns images
Clemens Neudecker 78bfa97c06
Merge pull request from qurator-spk/resolving_issue_106
fix OCR-D regression
kba 84d05bd0ae s,url,local_filename,
vahidrezanezhad c10a525675 inference with batch size bigger than 1
cneud 7f99526b9d update Makefile model location
cneud 4f8210de71 update Makefile model location
vahidrezanezhad 6f4205ba49 update pyproject.toml
vahidrezanezhad 74eac4dacc dtype = object in the case of length 1 arise error
cneud 8f76966394 update pyproject.toml for v0.3.1
cneud 28ee1e527e update pyproject.toml for v0.3.1
vahidrezanezhad 4c50479cb8 pyproject.toml may work for ocrd
vahidrezanezhad 53fd5fb2a5 resolving for pyproject.toml test
vahidrezanezhad e976778796 testing pyproject.toml
Clemens Neudecker 23ac58405c
update pyproject.toml
vahidrezanezhad e3edb0ec30 update
vahidrezanezhad 8e2cdad1be extracting images only - avoid artifacts with heuristics
vahidrezanezhad 00bf2b64d0 1&2 column images only printspace
vahidrezanezhad be144db9f8 updating 1&2 columns images + full layout
vahidrezanezhad a62ae370c3 new full layout model and early layout for 1&2 column images are integrated - light version
vahidrezanezhad 9170a9f21c only images extraction - update inference parameters
cneud f0e7f75499 Update README.md
cneud 7ded54a8d2 rename GH action
cneud c9f63826c0 create draft pyproject.toml
cneud 8862df9156 format options table
cneud 38698c6609 Update README.md
cneud 40f5408b1e improve huggingface url
cneud 3cfa447e84 remove CircleCI
cneud ad133e3425 Update model download url
vahidrezanezhad 5144668834 ocr engine first integration
vahidrezanezhad 721d3f70a0
Merge pull request from bertsky/new-namespace-pkg
non-legacy namespace package
Robert Sachunsky 45bd76f5e8 fix namespace pkg setup
Robert Sachunsky f88ee99f3c
non-legacy namespace package
Clemens Neudecker 899bb9f00c
update GitHub actions
Clemens Neudecker ba64282118
Update README.md