qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2026-06-28 07:49:21 +02:00
Code Issues Projects Releases Wiki Activity
1419 commits 27 branches 23 tags 12 MiB
Commit graph

524 commits

Author SHA1 Message Date
kba
f0c86672f8 adopt mb_ro_on_layout to the zoo 2025-10-21 17:55:08 +02:00
kba
bcffa2e503 adopt binarizer to the zoo 2025-10-21 17:53:24 +02:00
kba
a53d5fc452 update docs/makefile to point to v0.6.0 models 2025-10-21 13:15:57 +02:00
kba
c6b863b13f typing and asserts 2025-10-21 12:05:27 +02:00
kba
44b75eb36f cli: model -> model_basedir 2025-10-21 11:05:12 +02:00
kba
062f317d2e Introduce model_zoo to Eynollah_ocr 2025-10-20 21:14:52 +02:00
kba
d609a532bf organize imports mostly 2025-10-20 19:46:07 +02:00
kba
48d1198d24 move Eynollah_ocr to separate module 2025-10-20 19:15:31 +02:00
kba
a850ef39ea factor model loading in Eynollah to EynollahModelZoo 2025-10-20 18:34:44 +02:00
Robert Sachunsky
5a0e4c3b0f find_number_of_columns_in_document: improve splitter rule 
extend horizontal separators to full img width if they do not overlap
any other regions

(only as regards to returned `splitter_y` result,
 but without changing returned separators mask)
 2025-10-20 17:41:50 +02:00
Robert Sachunsky
542d38ab43 find_number_of_columns_in_document: simplify, rename line→seps 2025-10-20 17:41:49 +02:00
Robert Sachunsky
d3d599b010 order_of_regions: add better plotting (but commented out) 2025-10-20 17:41:47 +02:00
Robert Sachunsky
c43a825d1d order_of_regions: filter out-of-image peaks 2025-10-20 17:41:47 +02:00
Robert Sachunsky
48761c3e12 find_num_col: simplify, add better plotting (but commented out) 2025-10-20 17:41:45 +02:00
Robert Sachunsky
184927fb54 find_num_cols: re-sort peaks when cutting n-best num_col_classifier 2025-10-20 17:41:44 +02:00
Robert Sachunsky
086c1880ac binarization: add option --overwrite, skip existing outputs 
(also, simplify `run` and separate `run_single`)
 2025-10-20 17:40:52 +02:00
kba
6c89888166 Refactor CLI for consistent logging and late imports 2025-10-17 17:47:59 +02:00
kba
557fb227f3 training/gt_gen_utils: fix type errors, comment out dead code 2025-10-17 14:21:05 +02:00
kba
af74890b2e training/inference.py: add typing info, organize imports 2025-10-17 14:07:43 +02:00
kba
3a73ccca2e training/models.py: make imports explicit 2025-10-17 13:45:44 +02:00
kba
38c028c6b5 📦 v0.6.0 2025-10-17 10:36:30 +02:00
kba
76c13bcfd7 Merge branch 'integrate-training-from-sbb_pixelwise_segmentation' of https://github.com/qurator-spk/eynollah into integrate-training-from-sbb_pixelwise_segmentation 2025-10-16 20:50:24 +02:00
kba
af5abb77fd Merge branch 'main' into integrate-training-from-sbb_pixelwise_segmentation 2025-10-16 20:50:16 +02:00
Robert Sachunsky
948c8c3441 join_polygons: try to catch rare case of MultiPolygon 2025-10-15 16:58:17 +02:00
kba
f485dd4181 📦 v0.6.0rc2 2025-10-14 16:10:50 +02:00
kba
7daa0a1bd5 Merge branch 'fix-196' into prepare-v0.6.0rc2 2025-10-14 14:52:36 +02:00
Robert Sachunsky
8299e7009a setup_models: avoid unnecessarily loading region_fl 2025-10-14 14:27:32 +02:00
Robert Sachunsky
e8b7212f36 polygon2contour: avoid uint for coords 
(introduced in a433c736 to make consistent with
 `filter_contours_area_of_image`, but actually
 np.uint is prone to create overflows downstream)
 2025-10-14 14:27:26 +02:00
kba
745cf3be48 XML encoding should be utf-8 not utf8 
... and  should use OCR-D's generateDS PAGE API consistently
 2025-10-10 16:39:17 +02:00
kba
2056a8bdb9 📦 v0.6.0rc1 2025-10-10 16:32:47 +02:00
Robert Sachunsky
4e9a1618c3 layout: refactor model setup, allow loading custom versions 
- simplify definition of (defaults for) model versions
- unify loading of loadable models (depending on mode)
- use `self.models` dict instead of `self.model_*` attributes
- add `model_versions` kwarg / `--model_version` CLI option
 2025-10-10 03:18:09 +02:00
Robert Sachunsky
c4cb16c2a8 simplify 
(`skip_layout_and_reading_order` is already an attr)
 2025-10-09 23:05:50 +02:00
Robert Sachunsky
ecb53056f2 Merge branch 'main' of https://github.com/qurator-spk/eynollah into loky-with-shm-for-175-rebuilt 2025-10-09 22:54:11 +02:00
Robert Sachunsky
b3d29bef89 return_contours_of_interested_region*: rm unused variants 2025-10-09 20:14:11 +02:00
Robert Sachunsky
8a2d682e12 fix identifier scope in layout OCR options (w/o full_layout) 2025-10-09 20:14:11 +02:00
Robert Sachunsky
096def1e9d mbreorder/enhancment: fix missing imports 
(not sure if these models really need that, though)
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
027b87d321 fixup c0137c2 (missing arguments for utils_ocr) 2025-10-09 20:14:11 +02:00
Robert Sachunsky
1d4815b48f utils_ocr: forgot to pass coordinate offsets 2025-10-09 20:14:11 +02:00
Robert Sachunsky
5e11a68a3e writer/run_single: consistent kwarg naming conf_contours_textregion(s) 2025-10-09 20:14:11 +02:00
Robert Sachunsky
75823f9bed run_single: call writer.build_pagexml_no_full_layout w/ kwargs 2025-10-09 20:14:11 +02:00
Robert Sachunsky
cbbb3248c7 writer: simplify 
- `build_pagexml_no_full_layout`: delegate to
  `build_pagexml_full_layout` (removing redundant code)
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
e32479765c writer: simplify 
- simplify serialization of coordinates
- re-use `serialize_lines_in_region` (drop `*_in_dropcapital` and `*_in_marginal`)
- re-use `calculate_polygon_coords`
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
d88ca18eec get/do_work_of_slopes etc.: reduce call/return signatures 
- `get_textregion_contours_in_org_image_light`: no more need
  to also return unchanged contours here (see 41cc38c5); therefore
- `txt_con_org`: no more need for this
  (now mere alias to `contours_only_text_parent`); also
- `index_by_text_par_con`: no more need for this (see prev. commit),
  so do not pass/return
- `get_slopes_and_deskew_*`: do not pass `contours_only_text`
  (where not used)
- `get_slopes_and_deskew_*`: do not return unchanged contours, boxes
- `do_work_of_slopes_*`: adapt respectively
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
02a347a48a no more need to rm from contours_only_text_parent_d_ordered now 2025-10-09 20:14:11 +02:00
Robert Sachunsky
fd43e78442 filter_contours_without_textline_inside: simplify 
- np.delete in index array instead of contour lists
- yield actual resulting indices
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
0a80cd5dff avoid unnecessary 3-channel conversions: for tables, too 2025-10-09 20:14:11 +02:00
Robert Sachunsky
dfdc705375 do_work_of_slopes: rm unused old variant 2025-10-09 20:14:11 +02:00
Robert Sachunsky
2e907875c1 get_text_region_boxes_by_given_contours: simplify 2025-10-09 20:14:11 +02:00
Robert Sachunsky
d53f829dfd filter_contours_inside_a_bigger_one: fix edge case in 81827c29 2025-10-09 20:14:11 +02:00
Robert Sachunsky
595ed02743 run_single: simplify; allow running TrOCR in non-fl mode, too 
- refactor final `self.full_layout` conditional, removing copied code
- allow running `self.ocr` and `self.tr` branch in both cases (non/fl)
- when running TrOCR, use model / processor / device initialised during init
  (instead of ad-hoc loading)
 2025-10-09 20:14:11 +02:00