vahidrezanezhad
a62ae370c3
new full layout model and early layout for 1&2 column images are integrated - light version
2024-08-07 02:21:01 +02:00
vahidrezanezhad
5144668834
ocr engine first integration
2024-07-17 10:01:37 +02:00
vahidrezanezhad
eac18c553d
machine based reading order as an argument
2023-12-13 01:44:51 +01:00
vahidrezanezhad
941d87328a
machine based reading order & works for not full layout case
2023-10-20 11:19:30 +02:00
vahidrezanezhad
59c0d90e5a
machine based reading order inference & optimized algorithm
2023-10-20 10:17:46 +02:00
vahidrezanezhad
49c93149a4
machine based reading order inference with a variable batch size
2023-10-20 10:01:28 +02:00
vahidrezanezhad
5fdc6d4fa4
integration of machine based reading order detection
2023-10-14 09:05:05 +02:00
vahidrezanezhad
fc9e9cc29f
Merge pull request #117 from qurator-spk/tf-2.12-or-greater
...
Update tensorflow
2023-09-29 05:30:19 -04:00
cneud
4254ce3bdb
Update README.md
2023-09-26 18:54:14 +02:00
cneud
56934c876a
remove duplicate test for Python 3.8
2023-09-26 18:53:10 +02:00
Clemens Neudecker
6c65fc4dfe
Update config.yml
2023-09-26 18:33:05 +02:00
Clemens Neudecker
9d3a1a5b76
Update test-eynollah.yml
2023-09-26 18:32:20 +02:00
Clemens Neudecker
03bfd7a390
Update requirements.txt
...
Update to `tensorflow>=2.12` (drops Python 3.7 support)
* fix #114
* fix #115
Tested by @vahidrezanezhad @cneud
2023-09-26 18:16:20 +02:00
vahidrezanezhad
7a70b20c77
apply missed commit # a56988a back
2023-09-05 13:43:11 +02:00
vahidrezanezhad
0ea90b7509
Merge pull request #116 from qurator-spk/fix-typos
...
fix some typos
2023-08-18 08:23:23 -04:00
vahidrezanezhad
830b0fc8fa
Merge pull request #113 from qurator-spk/tf_<2.12.0
...
introduce (temporary) upper bounds for tensorflow and numpy version
2023-08-18 08:03:04 -04:00
cneud
d3b06baa84
fix some typos
2023-08-18 02:52:49 +02:00
Clemens Neudecker
3e62657570
added the TF upper bound in the README
2023-08-17 23:02:10 +02:00
Clemens Neudecker
b58a327c5d
cap numpy to <1.24.0
...
OK so now numpy is the culprit (shipped unbound via ocrd) which had several deprecations expire with release of v1.24.0 that require changes to our codebase, e.g.
* The deprecation for the aliases np.object, np.bool, np.float, np.complex, np.str, and np.int is expired
* Ragged array creation will now always raise a ValueError unless dtype=object is passed.
See also here: https://numpy.org/devdocs/release/1.24.0-notes.html#expired-deprecations
2023-08-17 22:07:45 +02:00
Clemens Neudecker
935332e863
test fix for keras.backend import error with Python 3.8
2023-08-17 21:45:48 +02:00
Clemens Neudecker
e5acee09ab
cap tensorflow version to <2.12.0
...
Cap tensorflow version to <2.12.0 until we have time to adapt to the API changes such as e.g.
* Support for Python 3.11 has been added.
* Support for Python 3.7 has been removed.
See also https://github.com/tensorflow/tensorflow/releases/tag/v2.12.0 .
2023-08-17 21:05:51 +02:00
Clemens Neudecker
6ba5cdcc11
Update citation
2023-08-14 22:16:51 +02:00
Clemens Neudecker
2db588a146
Update bibtex entry
2023-08-09 18:39:49 +02:00
Clemens Neudecker
aad80696e6
format citation info as bibtex
2023-06-23 14:04:24 +02:00
Clemens Neudecker
a0949fd74a
add HIP'23 paper reference
2023-06-23 13:54:04 +02:00
vahidrezanezhad
5f7d9a475c
Merge pull request #109 from bertsky/patch-3
...
pil_cv2.check_dpi: fix class membership test
2023-06-21 16:37:16 +02:00
Clemens Neudecker
bafad0c511
Merge pull request #105 from bertsky/fix-model-archive-path
...
update tool json resource path_in_archive
2023-06-19 12:54:47 +02:00
Robert Sachunsky
867a7261de
pil_cv2.check_dpi: fix class membership test
...
(depending on how the `PIL.Image` was instantiated – file plugin or array interface – the previous `isinstance` could fail, provoking a fall-through to `cv2pil` which does not work)
2023-06-12 00:45:57 +02:00
Robert Sachunsky
b049e475e3
update tool json resource path_in_archive
2023-06-10 11:14:27 +02:00
Clemens Neudecker
fbe2f2302f
Merge pull request #104 from bertsky/reinstate-namespace-pkg
...
Revert "Merge pull request #97 from qurator-spk/420-namespace-package"
2023-06-09 19:45:48 +02:00
Robert Sachunsky
69c1d6b3d6
Revert "Merge pull request #97 from qurator-spk/420-namespace-package"
...
This reverts commit fd56b86acfea792d1e4a
2023-06-09 19:22:34 +02:00
vahidrezanezhad
68923e0a5d
Merge pull request #102 from qurator-spk/right2left_reading_order
...
Right2left reading order
2023-06-05 18:59:33 +02:00
vahid
0b35011847
right2left reading order detection accomplished
2023-06-01 17:30:12 +02:00
vahid
0cda1f3c7a
reading order type 1: right to left
2023-05-26 15:08:27 +02:00
vahid
b01888da31
delete printing resized image shape
2023-05-19 14:50:59 +02:00
vahid
45c40a58fc
issue #67 solved
2023-05-19 14:48:56 +02:00
cneud
a96147b621
improve links to GT guidelines
2023-05-13 15:36:24 +02:00
cneud
c7057bad5e
Update README.md
2023-05-13 12:47:06 +02:00
cneud
419e589df7
Update CHANGELOG.md
2023-05-13 12:44:45 +02:00
cneud
6eab7a60a9
Update ocrd-tool.json
2023-05-13 12:42:05 +02:00
Clemens Neudecker
fd9431a678
Merge pull request #86 from qurator-spk/eynollah_light
...
Eynollah light integration
2023-05-13 03:08:05 +02:00
cneud
48f2ce6203
re-enable Action for Python 3.8
2023-05-13 02:39:18 +02:00
vahidrezanezhad
1621532092
Merge branch 'main' into eynollah_light
2023-05-09 00:46:58 +02:00
vahid
4c217018cc
textline light version -tll can not work without enabling -light option
2023-04-27 21:07:33 +02:00
vahid
d68f240b59
loading TensorFlow SavedModel format is now present
2023-04-27 17:05:21 +02:00
vahid
380f59ad67
let hybrid textline light model be loaded
2023-04-18 15:06:18 +02:00
vahidrezanezhad
29e6ad076f
renaming textline light model
2023-04-18 13:47:43 +02:00
Robert Sachunsky
529f2c0e19
set_memory_growth to all GPU devices alike
2023-04-14 20:04:34 +02:00
vahidrezanezhad
52d2e0b098
Merge pull request #100 from bertsky/patch-2
...
set_memory_growth to all GPU devices alike
2023-04-14 17:40:56 +02:00
Clemens Neudecker
cb5ffaee14
Update README.md
2023-04-14 13:24:13 +02:00
