Commit graph

155 commits

Author SHA1 Message Date
Alexander Pacha
3ade5eccba
Merge pull request #1 from bertsky/batch-prediction
fixup for batch prediction PR
2023-03-19 07:59:36 +01:00
Robert Sachunsky
6dc83dd1a5 comment out explicit GC calls / session management 2023-02-14 23:34:27 +00:00
Robert Sachunsky
4086c6956a adapt OCR-D wrapper 2023-02-14 23:33:56 +00:00
Robert Sachunsky
342e94e287 reinstate ensemble combination and in-memory prediction 2023-02-14 23:33:35 +00:00
Robert Sachunsky
cade5dda73 reintroduce TF stderr / log silencer 2023-02-14 23:09:40 +00:00
Alexander Pacha
9ef8259677 Merge branch 'master-upstream'
# Conflicts:
#	README.md
#	sbb_binarize/cli.py
#	sbb_binarize/sbb_binarize.py
2022-11-22 16:10:22 +01:00
Konstantin Baierer
aeb6804b7d 📦 v0.0.11 2022-10-24 16:57:22 +02:00
Konstantin Baierer
82816b048e 📝 changelog 2022-10-24 16:56:22 +02:00
Konstantin Baierer
6fb6946531
Merge pull request #53 from bertsky/patch-3
ocrd-tool.json: register SavedModel resources
2022-10-24 16:54:22 +02:00
Clemens Neudecker
0d8a9f33f5
Update README.md
remove patches parameter from readme
2022-10-12 00:29:22 +02:00
vahid
7c3f2176f7 issue #45 the patches option is omitted and it means that documents will be processed in patches while no patches is not desired by the tool 2022-10-11 19:18:40 +02:00
Robert Sachunsky
743ca0dbed
Update requirements.txt 2022-10-11 17:20:31 +02:00
Robert Sachunsky
f8ade5d3da
ocrd-tool.json: register SavedModel resources 2022-10-11 17:19:30 +02:00
Clemens Neudecker
eff7a47852
Merge pull request #52 from bertsky/img-allow-alpha
allow alpha channels
2022-10-11 13:11:44 +02:00
Clemens Neudecker
56ccb39539
Update README
* recommend cropping (fix #49)
* document huggingface saved_model
2022-10-11 11:37:00 +02:00
Robert Sachunsky
a69470135a load_model: also allow SavedModel directories 2022-10-11 07:21:17 +00:00
Robert Sachunsky
88d64de67b pil2cv: reduce transparency to white 2022-10-11 07:20:38 +00:00
Alexander Pacha
4a97eacc56 Removed --patches flag, as the new version automatically uses patches in an efficient way.
Updated cli.py to correctly load and initialize the changed SbbBinarizer class
2022-09-15 10:53:14 +02:00
Alexander Pacha
7edf34a815 Adding a bit more documentation 2022-08-30 11:54:04 +02:00
Alexander Pacha
9db2bcc8b0 Remove obsolete comment 2022-08-30 11:44:15 +02:00
Alexander Pacha
1c7e8c5e21 Improved formatting 2022-08-30 11:00:25 +02:00
Alexander Pacha
1baa70e382 Improving comments in the code 2022-08-30 10:58:45 +02:00
Alexander Pacha
4112c6fe71 Rewrote binarization script to always use patches, but in a much more efficient way and adding support for batch-conversion with multiple GPUs. 2022-08-30 10:58:45 +02:00
Alexander Pacha
b0a8b613e8 Improved loading of models to allow providing a directory, added a few type-hints and improved the code-style a little bit by running an auto-formatter on the entire file. 2022-08-30 10:58:45 +02:00
vahid
f11d0b0bf7 #42 is resolved 2022-08-25 23:51:16 +02:00
vahidrezanezhad
2355d0ec8f
Merge pull request #43 from apacha/fix_no_models_available
Raise error when no models were loaded
2022-08-25 14:55:35 +02:00
Alexander Pacha
55a9fba677 Small fix to raise an exception when no model was found instead of failing later with TypeError: 'int' object is not subscriptable. 2022-08-22 10:36:43 +02:00
Konstantin Baierer
c99be55af2 📦 v0.0.10 2022-07-21 15:00:31 +02:00
Konstantin Baierer
2abd8ae848 📝 changelog 2022-07-21 14:59:10 +02:00
Konstantin Baierer
d1e9389b54
Merge pull request #40 from maxnth/fix/cli
use types.Path instead of click.Path to avoid NameError
2022-07-21 14:48:31 +02:00
maxnth
dc5a5c791a use types.Path instead of click.Path to avoid NameError 2022-07-21 10:37:30 +02:00
Clemens Neudecker
e4c1eb2913
Merge pull request #37 from bertsky/patch-2
depend on tensorflow not tensorflow-gpu, drop holding h5py
2022-05-03 22:49:41 +02:00
Robert Sachunsky
fd93a45505
depend on tensorflow not tensorflow-gpu, drop holding h5py 2022-05-03 22:25:51 +02:00
Clemens Neudecker
0877199c68
importing types from click is enough 2022-04-26 18:24:35 +02:00
vahidrezanezhad
792619e830
Update cli.py 2022-04-26 13:16:09 +02:00
vahidrezanezhad
82e0783e01
fixing #30. Directory of model(s) is needed not model file name. 2022-04-26 13:14:04 +02:00
Clemens Neudecker
2119c907c4
Merge pull request #36 from qurator-spk/0.0.9
v0.0.9
2022-04-26 11:12:54 +02:00
Clemens Neudecker
aab51dbe82
Update ocrd-tool.json 2022-04-25 21:28:25 +02:00
Clemens Neudecker
b9bbbe9004
Update CHANGELOG.md 2022-04-25 21:27:42 +02:00
Clemens Neudecker
ff78d4e85c
improve usage instructions 2022-04-25 19:24:04 +02:00
vahidrezanezhad
0fe5232488
Merge pull request #35 from cneud/upgrade_to_tf2_with_tf1.compat_session
fix tf2 with tf1.compat session
2022-04-25 16:52:26 +02:00
Clemens Neudecker
2d4ce8f706
don't require Keras explicitely 2022-04-25 15:21:43 +02:00
Clemens Neudecker
83c60d7b26
cleanup 2022-04-25 15:10:08 +02:00
cneud
b7aeb1ae8b use tensorflow Keras backend 2022-04-25 14:27:39 +02:00
Clemens Neudecker
1a4207c614
relax numpy version requirement 2022-04-25 11:55:06 +02:00
Clemens Neudecker
df8e7bfb33
Update requirements.txt 2022-04-25 11:53:45 +02:00
vahid
6296c6a82c Revert "Merge pull request #34 from qurator-spk/upgrade_to_tf2_with_compat_mode"
This reverts commit 593458d321, reversing
changes made to e1575268d7.
2022-04-25 11:21:37 +02:00
vahidrezanezhad
593458d321
Merge pull request #34 from qurator-spk/upgrade_to_tf2_with_compat_mode
actually use TF2 (with TF1.compat mode)
2022-04-25 10:36:29 +02:00
Clemens Neudecker
33deaaa90d
actually use TF2 (with TF1.compat mode) 2022-04-21 13:39:27 +02:00
vahidrezanezhad
e1575268d7
Merge pull request #31 from bertsky/factor-setup
Factor setup
2022-04-20 15:39:32 +02:00