vahidrezanezhad
|
3095498162
|
loading savedmodel format and saving as png
|
2024-08-20 15:46:20 +02:00 |
|
vahid
|
5c37d18cb0
|
enable flowing from directory
|
2022-05-03 14:00:24 +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
|
aab51dbe82
|
Update ocrd-tool.json
|
2022-04-25 21:28:25 +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 |
|
Robert Sachunsky
|
73b7b48dfb
|
ocrd-tool.json: add directory content-type for model
|
2022-02-10 16:19:13 +01:00 |
|
Robert Sachunsky
|
416b5dd7e2
|
adapt to TF1 deprecation
|
2021-06-10 21:09:11 +02:00 |
|
Robert Sachunsky
|
ad50ed287d
|
binarizer: reset TF session prior to predict()
|
2021-06-10 01:22:28 +02:00 |
|
Robert Sachunsky
|
02423648ec
|
OCR-D CLI: encapsulate model loading into setup(), triggered by init
|
2021-06-10 01:19:43 +02:00 |
|
Konstantin Baierer
|
8dd05064b2
|
📦 v0.0.8
|
2021-05-07 17:20:08 +02:00 |
|
vahid
|
2c7cd84649
|
resolving error for inputs whcih have smaller scale than model patch
|
2021-03-22 19:59:55 +01:00 |
|
Konstantin Baierer
|
f41cd58550
|
extract page_image also for operation_level region
|
2021-03-22 15:44:04 +01:00 |
|
Konstantin Baierer
|
4a5544d985
|
📦 v0.0.7
|
2021-02-02 17:47:35 +01:00 |
|
Konstantin Baierer
|
a3b1e721b2
|
ocrd-cli: fix indentation
|
2021-01-28 14:16:02 +01:00 |
|
Konstantin Baierer
|
4ceed759ad
|
processor: self.resolve_resource model in addition to SBB_BINARIZE_DATA
|
2021-01-28 12:44:47 +01:00 |
|
Konstantin Baierer
|
ea69494d2a
|
📦 v0.0.6
|
2020-11-23 11:04:30 +01:00 |
|
Konstantin Baierer
|
c9e41727bf
|
📦 v0.0.5
|
2020-11-02 12:11:21 +01:00 |
|
Lucas Sulzbach
|
45f1509dbc
|
sbb_binarize: Load each model only once
|
2020-11-01 11:26:48 -03:00 |
|
Lucas Sulzbach
|
0f7d4c589a
|
sbb_binarize: Start new session only once
|
2020-11-01 10:08:32 -03:00 |
|
Konstantin Baierer
|
b98d7f51ae
|
📦 v0.0.4
|
2020-10-27 14:33:10 +01:00 |
|
vahidrezanezhad
|
f363063e75
|
Merge pull request #9 from OCR-D/envvar-continued
combine SBB_BINARIZE_DATA and model parameter
|
2020-10-27 13:30:43 +01:00 |
|
Konstantin Baierer
|
6ebd6f0d45
|
📦 v0.0.3
|
2020-10-23 19:39:09 +02:00 |
|
Konstantin Baierer
|
e46b89af85
|
Merge branch 'release-v0.0.2' into release-v0.0.3
|
2020-10-23 19:35:44 +02:00 |
|
Konstantin Baierer
|
71b2801183
|
🐛 read from image_path, not image
|
2020-10-23 19:23:59 +02:00 |
|
Konstantin Baierer
|
b10b49c6ce
|
📦 v0.0.2
|
2020-10-23 17:09:54 +02:00 |
|
Clemens Neudecker
|
4d145cc905
|
Merge pull request #11 from OCR-D/altimage-comments
🐛 typo: comment{,s}, fix #8
|
2020-10-23 15:49:34 +02:00 |
|
Konstantin Baierer
|
c4b63fca47
|
🐛 typo: comment{,s}, fix #8
|
2020-10-23 13:51:52 +02:00 |
|
Konstantin Baierer
|
664a441a2d
|
glob *.h5 files only in model dir, fix #7
|
2020-10-23 11:30:31 +02:00 |
|
Konstantin Baierer
|
b62b32c998
|
combine SBB_BINARIZE_DATA and model parameter
|
2020-10-23 11:19:14 +02:00 |
|
Konstantin Baierer
|
0c31eaf6b1
|
ocrd cli: "model" parameter replaceable by SBB_BINARIZE_DATA envvar
|
2020-10-22 18:37:08 +02:00 |
|
Konstantin Baierer
|
84d6b1f693
|
🐛 numpy.ndarray.as{_,}type
|
2020-10-16 17:24:55 +02:00 |
|
Konstantin Baierer
|
6543e74deb
|
remove "patches" parameter, always use_patches
|
2020-10-16 12:52:16 +02:00 |
|
Konstantin Baierer
|
2bc6ccc4c0
|
replace patches string comparison with use_patches boolean
|
2020-10-16 12:50:32 +02:00 |
|
Konstantin Baierer
|
fad7b7aff1
|
rewrite "normal" CLI with click
|
2020-10-16 12:48:32 +02:00 |
|
Konstantin Baierer
|
645ec4124a
|
ocrd-tool: disable "line" level-of-operation for now
|
2020-10-16 12:35:58 +02:00 |
|
Konstantin Baierer
|
1fa581283c
|
SbbBinarizer: refactor (variable names, less instance-wide state)
|
2020-10-16 12:30:51 +02:00 |
|
Konstantin Baierer
|
a1c8f6f465
|
line-level binarization independent of region-level
|
2020-10-16 11:53:26 +02:00 |
|
Konstantin Baierer
|
e5bc5572a2
|
change description ht @bertsky @vahidrezanezhad
|
2020-10-16 11:31:14 +02:00 |
|
Konstantin Baierer
|
b7a6301948
|
fix cv2pil ht @bertsky
|
2020-10-16 11:27:37 +02:00 |
|
Konstantin Baierer
|
eece89b9ac
|
patches should be true by default, ht @vahidrezanezhad
|
2020-10-16 11:12:17 +02:00 |
|
Konstantin Baierer
|
2eec6876fa
|
Append "binarized" to AlternativeImage/comments
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
|
2020-10-16 11:01:11 +02:00 |
|
Konstantin Baierer
|
ee82d188bf
|
Set page_id from input file
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
|
2020-10-16 11:00:18 +02:00 |
|
Konstantin Baierer
|
0650bad533
|
image_from_segment: exclude already binarized images
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
|
2020-10-16 10:59:42 +02:00 |
|
Konstantin Baierer
|
12b44af329
|
convert between cv2 and pil, DRY binarizer call
|
2020-10-15 18:10:06 +02:00 |
|
Konstantin Baierer
|
a4c0cf0a47
|
shut up keras/tensorflow
|
2020-10-15 17:26:13 +02:00 |
|
Konstantin Baierer
|
d4c97ebf72
|
add OCR-D click interface
|
2020-10-15 17:12:17 +02:00 |
|
Konstantin Baierer
|
ee26ebd7d8
|
implement region/line binarization
|
2020-10-15 16:55:17 +02:00 |
|