e976778796
testing pyproject.toml
9 months ago
23ac58405c
update pyproject.toml
9 months ago
e3edb0ec30
update
9 months ago
8e2cdad1be
extracting images only - avoid artifacts with heuristics
9 months ago
00bf2b64d0
1&2 column images only printspace
9 months ago
be144db9f8
updating 1&2 columns images + full layout
9 months ago
a62ae370c3
new full layout model and early layout for 1&2 column images are integrated - light version
9 months ago
9170a9f21c
only images extraction - update inference parameters
9 months ago
f0e7f75499
Update README.md
10 months ago
7ded54a8d2
rename GH action
10 months ago
c9f63826c0
create draft pyproject.toml
10 months ago
8862df9156
format options table
10 months ago
38698c6609
Update README.md
10 months ago
40f5408b1e
improve huggingface url
10 months ago
3cfa447e84
remove CircleCI
10 months ago
ad133e3425
Update model download url
10 months ago
5144668834
ocr engine first integration
10 months ago
721d3f70a0
Merge pull request #127 from bertsky/new-namespace-pkg
...
non-legacy namespace package
12 months ago
45bd76f5e8
fix namespace pkg setup
12 months ago
f88ee99f3c
non-legacy namespace package
12 months ago
899bb9f00c
update GitHub actions
1 year ago
ba64282118
Update README.md
1 year ago
533736a3e3
update supported Python+Tensorflow version combinations
1 year ago
b3fa684395
pin tf2 version to 2.12.1
...
until we fix keras compatibility
1 year ago
f09b7c1bef
use tf1 compatibility for keras backend
1 year ago
eac18c553d
machine based reading order as an argument
1 year ago
7cbca79f16
replacing images cotour with bounding box
1 year ago
aa41e4df20
The contours of images can now be written in an XML file
1 year ago
364ccacab2
adding extracting images only in cli
1 year ago
6aac0b8faf
avoiding artifact images on the boundary of documents
1 year ago
e7d12d3549
first update for only images extraction
1 year ago
6018b354aa
comment unnecessary print commands
1 year ago
f2811ee469
add supported OS to readme
2 years ago
941d87328a
machine based reading order & works for not full layout case
2 years ago
59c0d90e5a
machine based reading order inference & optimized algorithm
2 years ago
49c93149a4
machine based reading order inference with a variable batch size
2 years ago
7983a65006
filtering separators in a correct way without missing them
2 years ago
5fdc6d4fa4
integration of machine based reading order detection
2 years ago
fc9e9cc29f
Merge pull request #117 from qurator-spk/tf-2.12-or-greater
...
Update tensorflow
2 years ago
4254ce3bdb
Update README.md
2 years ago
56934c876a
remove duplicate test for Python 3.8
2 years ago
6c65fc4dfe
Update config.yml
2 years ago
9d3a1a5b76
Update test-eynollah.yml
2 years ago
03bfd7a390
Update requirements.txt
...
Update to `tensorflow>=2.12` (drops Python 3.7 support)
* fix #114
* fix #115
Tested by @vahidrezanezhad @cneud
2 years ago
7a70b20c77
apply missed commit #a56988a back
2 years ago
0ea90b7509
Merge pull request #116 from qurator-spk/fix-typos
...
fix some typos
2 years ago
830b0fc8fa
Merge pull request #113 from qurator-spk/tf_<2.12.0
...
introduce (temporary) upper bounds for tensorflow and numpy version
2 years ago
d3b06baa84
fix some typos
2 years ago
3e62657570
added the TF upper bound in the README
2 years ago
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
2 years ago
vahidrezanezhad
Clemens Neudecker
Robert Sachunsky
Robert Sachunsky