0a9dbd0c25
🧹 Do not install numpy, let the TF dependency do it
2020-07-23 13:04:11 +02:00
d9afb05cf3
🐛 Use TensorFlow >= 2.3.0rc2 to fix retracing warnings
2020-07-23 12:44:15 +02:00
4eb4f97f6b
Merge branch 'feat/update-calamari1' of https://github.com/OCR-D/ocrd_calamari into feat/update-calamari1
2020-07-23 12:34:27 +02:00
93190fae3b
⚡ Recognize more than one line at a time (Fixes gh#20)
2020-07-22 16:03:10 +02:00
7584d0135c
⬆️ Update model download for Calamari 1.0
2020-07-21 20:18:29 +02:00
9ea50e25d1
⬆️ Update to Calamari 1.0.x
2020-07-21 20:18:29 +02:00
027fcd7d75
🐛 Fix test file path
2020-07-21 20:10:36 +02:00
8ab57e44dc
⬆️ Update model download for Calamari 1.0
2020-07-21 18:52:47 +02:00
7dff7784c5
⬆️ Update to Calamari 1.0.x
2020-07-21 18:16:52 +02:00
c6ced9b3e9
Merge pull request #39 from OCR-D/dont-install-test
...
setup.py: exclude "test", not "tests", from installation
2020-06-04 12:07:03 +02:00
kba
e03ff4064b
setup.py: exclude "test", not "tests", from installation
2020-05-31 20:31:06 +02:00
fb538845d8
📄 Update license ( Fixes #35 )
...
Set copyright owner name. Also, going along the lines of "update the year when substantial revision of the work happenend", set the copyright years. The latter may be not be necessary, because "life of author + 70 years" or something.
2020-02-13 16:49:11 +01:00
123ee61a8b
v0.0.6
2020-02-13 16:04:17 +01:00
69df78bce1
🐛 setup.py: Fix GitHub url by s/kba/OCR-D
2020-02-13 16:02:02 +01:00
62e5e0c295
🐛 ocrd-tool.json: Fix GitHub url by s/kba/OCR-D
2020-02-13 16:00:58 +01:00
0334a35870
🐛 Sort predictions in exactly the same way, also when building the text
2020-02-12 17:18:37 +01:00
0c9e1f13c7
🐛 Sort predictions in exactly the same way to make sure we are correctly removing spaces
2020-02-12 16:38:45 +01:00
d2c843aa3f
📦 v0.0.5
2020-02-12 13:33:38 +01:00
cd8f6a5fcb
🐛 Use line id for debug message
2020-02-12 13:32:10 +01:00
5b6d8b3f41
🐛 Build line text on our own
...
Calamari does whitespace post-processing on prediction.sentence, while
it does not do the same on prediction.positions. Do it on our own to
have consistency.
Fixes GH-37.
2020-02-12 12:25:25 +01:00
30f7e1b246
🐳 Docker: Run pip3 check for good measure
2020-02-06 14:01:36 +01:00
303172b279
📝 Document make targets
2020-02-06 13:53:55 +01:00
a2d1d76dbd
🐳 Docker: Do not use the make target to install calamari-ocr, stick to pip
2020-02-06 13:52:05 +01:00
41f5c8a8fa
🐳 Docker: Upgrade pip to silence warning and fix potential other problems
2020-02-06 13:44:43 +01:00
7c18b1d391
🐳 Docker: Use ocrd/core:master instead of outdated :edge
2020-02-06 13:43:59 +01:00
1fda419f25
🐳 Fix Docker build
2020-02-06 13:43:36 +01:00
71096493ac
📝 README-DEV: Improve info about releasing
2020-02-06 13:04:29 +01:00
b26194179c
📝 README-DEV: Improve markdown
2020-02-06 13:03:06 +01:00
cf7a788854
📝 README-DEV: Mention cleaning up the dict/ directory
2020-02-06 13:02:02 +01:00
4508e3ec47
📦 v0.0.4
2020-02-05 17:55:51 +01:00
73beab1770
📝 README: Add a missing cd
2020-02-05 17:49:31 +01:00
3416a155ec
📝 README: Provide a complete example using real data and other processors
...
See #33 .
2020-02-05 17:39:49 +01:00
f2001a79f1
Merge branch 'master' of https://github.com/OCR-D/ocrd_calamari
2020-02-05 16:19:12 +01:00
3e426b2a0a
📝 README: Use gt4histocr-calamari from the Makefile in the example
...
See #33 .
2020-02-05 16:18:30 +01:00
46fe34400f
📝 README: Link to the correct ocrd-tool.json
2020-02-05 13:33:52 +01:00
0c7cd69526
📝 README: Update intro that we're mostly on par with Calamari's functionality
2020-02-05 13:33:02 +01:00
b802b4deaf
✨ Allow configuring a cut off confidence value for glyph alternatives
2020-02-05 13:29:44 +01:00
e39a2bce01
📝 Fix example parameters JSON
2020-02-05 13:07:56 +01:00
ef3fb44fb5
✨ Allow controlling of output hierarchy level, e.g. only line, not words+glyphs
2020-02-05 13:02:10 +01:00
0f0bae18ba
✅ Remove GT text to not accidently check it instead of OCR text
2020-02-04 19:29:56 +01:00
82fe0333f1
✅ Test word segmentation ( Fixes #30 )
2020-02-04 18:40:06 +01:00
9010250911
♻ test: Move binarization into the workspace fixture
2020-02-04 13:54:45 +01:00
6f4736f8e4
✨ Do word segmentation as expected by OCR-D PAGE specs
2020-02-03 19:10:16 +01:00
0f9c94e7dc
🐛 Start with TextEquiv index=1 to adhere to OCR-D PAGE conventions
...
https://ocr-d.github.io/page#multiple-textequivs
2020-02-03 17:40:45 +01:00
909632493b
🚧 Add future TODOs
2020-02-03 17:37:19 +01:00
3149e1d9e0
📝 unwanted()
2020-02-03 15:33:38 +01:00
91cca1e1b8
📝 Document why we are using Unicode text segmentation to produce word results
2020-02-03 15:33:11 +01:00
0a572df0ba
📝 README: Add information about the new glyph and word segmentation
2020-02-03 15:32:26 +01:00
2650189910
🧹 Add whitespace
2020-02-03 14:03:54 +01:00
f75426060e
🧹 Remove debugging print
2020-02-03 14:03:28 +01:00