qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-10-15 19:09:58 +02:00
Code Issues Projects Releases Wiki Activity
934 commits 21 branches 20 tags 22 MiB
Commit graph

934 commits

This branch
This branch
All branches
Author SHA1 Message Date
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
18bbdb7c48 CI: run deps-test with OCR extra so symlink rule fires 2025-10-09 20:14:11 +02:00
Robert Sachunsky
23535998f7 tests: symlink OCR models into layout model directory 
(so layout with OCR options works with our split model packages)
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
a1904fa660 tests: cover layout with OCR in various modes 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
Robert Sachunsky
6e57ab3741 textline_contours_postprocessing: do not catch arbitrary exceptions 2025-10-09 20:14:11 +02:00
Robert Sachunsky
fe603188f4 avoid unnecessary 3-channel conversions 2025-10-09 20:14:11 +02:00
Robert Sachunsky
155b8f68b8 matching deskewed text region contours with predicted: improve 
- avoid duplicate and missing mappings by using a different approach:
  instead of just minimising the center distance for the N contours
  that we expect,
  1. get all N:M distances
  2. iterate over them from small to large
  3. continue adding correspondences until both every original contour
     and every deskewed contour have at least one match
  4. where one original matches multiple deskewed contours,
     join the latter polygons to map as single contour
  5. where one deskewed contour matches multiple originals,
     split the former by intersecting with each of the latter
     (after bringing them into the same coordinate space),
     so ultimately only the respective match gets assigned
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
0e00d7868b matching deskewed text region contours with predicted: improve 
- apply same min-area filter to deskewed contours as to original ones
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
0f33c21eb3 matching deskewed text region contours with predicted: improve 
- when matching undeskewed and new contours, do not just
  pick the closest centers, respectively, but also of similar
  size (by making the contour area the 3rd dimension of the
  vector norm in the distance calculation)
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
73e5a1def8 matching deskewed text region contours with predicted: simplify 
- (no need for argmax if already sorted)
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
d774a23daa matching deskewed text region contours with predicted: simplify 
- avoid loops in favour of array processing
- improve readability and identifiers
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
29b4527bde do_order_of_regions: simplify 
- remove duplicate code via inline def for the try-catch
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
e674ea08f3 do_order_of_regions: drop redundant no/full_layout 
(`_no_full_layout` is the same copied code as `_full_layout`;
 the latter runs just the same if passed an empty list for headings)
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
e9bb62bd86 do_order_of_regions: simplify 
- avoid loops in favour of array processing
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
7387f5a929 do_order_of_regions: improve box matching, simplify 
- when searching for boxes matching contour, be more precise:
  - avoid heuristic rules ("xmin + 80 within xrange") in favour
    of exact criteria (contour properly contained in box)
  - for fallback criterion (nearest centers), also require
    proper containment of center in box
- `order_of_regions`: remove (now) unnecessary (and insufficient)
  workaround for missing indexes (if boxes are not covering contours
  exactly)
 2025-10-09 20:14:11 +02:00
Robert Sachunsky
4950e6bd78 order_of_regions: simplify 
- use new `find_center_of_contours`
- avoid unused calculations
- avoid loops in favour of array processing
 2025-10-09 20:14:10 +02:00
Robert Sachunsky
a1c8fd4467 do_order_of_regions / order_of_regions: simplify 
- array-convert only once (before returning from `order_of_regions`)
- avoid passing `matrix_of_orders` unnecessarily between
  `order_of_regions` and `order_and_id_of_texts`
 2025-10-09 20:14:10 +02:00
Robert Sachunsky
415b2cbad8 eynollah, drop_capitals: simplify 
- use new `find_center_of_contours`
 2025-10-09 20:14:10 +02:00
Robert Sachunsky
3f3353ec3a do_order_of_regions: simplify 
- avoid loops in favour of array processing
 2025-10-09 20:14:10 +02:00
Robert Sachunsky
8c3d5eb0eb separate_marginals_to_left_and_right_and_order_from_top_to_down: simplify 
- use new `find_center_of_contours`
- avoid loops in favour of array processing
- avoid repeated sorting
 2025-10-09 20:14:10 +02:00
Robert Sachunsky
81827c2942 filter_contours_inside_a_bigger_one: simplify 
- use new `find_center_of_contours`
- avoid loops in favour of array processing
- use sets instead of `np.unique` and `np.delete` instead of list.pop
 2025-10-06 13:32:34 +02:00
Robert Sachunsky
0b9d4901a6 contour features: avoid unused calculations, simplify, add shortcuts 
- new function: `find_center_of_contours`
- simplified: `find_(new_)features_of_contours`
 2025-10-02 20:51:03 +02:00
Robert Sachunsky
3aa7ad04fa 📝 update changelog 2025-09-30 23:14:52 +02:00
Robert Sachunsky
f0de1adabf rm loky dependency 2025-09-30 23:12:18 +02:00
Robert Sachunsky
7daec392b9 Dockerfile: fix up CUDA installation for mixed TF/Torch 2025-09-30 22:10:45 +02:00
Robert Sachunsky
ad129ed46c CI: remove OS from model cache keys 2025-09-30 22:05:53 +02:00
Robert Sachunsky
c86e59f481 CI: update model key, split up cache restore/save 2025-09-30 22:03:46 +02:00
Robert Sachunsky
a3d8197930 makefile: update model URL 2025-09-30 21:50:21 +02:00
Robert Sachunsky
61b20cc83d tests: switch from subtests to parametrize, use --isolate everywhere to free CUDA memory in between 2025-09-30 19:20:35 +02:00
Robert Sachunsky
375e0263d4 CNN-RNN OCR model: switch to 20250930 version (compatible with TF 2.12 on CPU as well) 2025-09-30 19:16:50 +02:00
Robert Sachunsky
b21051db21 ProcessPoolExecutor: shutdown during del() instead of atexit() 2025-09-30 19:16:00 +02:00
Robert Sachunsky
08c8c26028 indent extremely long lines 2025-09-30 03:52:19 +02:00
Robert Sachunsky
f857ee7b51 simplify 2025-09-30 02:26:00 +02:00
Robert Sachunsky
c0137c29ad try to fix the failed outsourcing of utils_ocr 2025-09-30 02:23:43 +02:00
Robert Sachunsky
13f85b0d5c Merge branch 'main' into loky-with-shm-for-175-rebuilt 2025-09-30 02:07:20 +02:00
Robert Sachunsky
758602403e replace loky with concurrent.futures.ProcessPoolExecutor (faster) 2025-09-29 17:48:22 +02:00
Robert Sachunsky
0366707136 get_smallest_skew: do not pass logger 2025-09-29 17:48:22 +02:00
Robert Sachunsky
b94c96fcbb find_num_col: exit early if empty (avoiding exceptions) 2025-09-29 17:48:22 +02:00
Robert Sachunsky
04c3d7dd1b get_smallest_skew: avoid shm if no ProcessPoolExecutor is passed 2025-09-29 17:48:22 +02:00
Robert Sachunsky
0662ece536 do_work_of_slopes*: use shm also in non-light mode(s) 2025-09-29 17:48:22 +02:00