vahid
|
0b35011847
|
right2left reading order detection accomplished
|
1 year ago |
|
vahid
|
0cda1f3c7a
|
reading order type 1: right to left
|
1 year ago |
|
vahid
|
b01888da31
|
delete printing resized image shape
|
2 years ago |
|
vahid
|
45c40a58fc
|
issue #67 solved
|
2 years ago |
cneud
|
6eab7a60a9
|
Update ocrd-tool.json
|
2 years ago |
vahidrezanezhad
|
1621532092
|
Merge branch 'main' into eynollah_light
|
2 years ago |
|
vahid
|
4c217018cc
|
textline light version -tll can not work without enabling -light option
|
2 years ago |
|
vahid
|
d68f240b59
|
loading TensorFlow SavedModel format is now present
|
2 years ago |
|
vahid
|
380f59ad67
|
let hybrid textline light model be loaded
|
2 years ago |
|
vahidrezanezhad
|
29e6ad076f
|
renaming textline light model
|
2 years ago |
Robert Sachunsky
|
529f2c0e19
|
set_memory_growth to all GPU devices alike
|
2 years ago |
|
Robert Sachunsky
|
8fe3567123
|
set_memory_growth to all GPU devices alike
|
2 years ago |
|
vahid
|
d3735b12f4
|
pushing commits 2d9ccac and 7345f6b into eynollah_light
|
2 years ago |
|
cneud
|
817e5a6af9
|
update docstring
|
2 years ago |
|
cneud
|
a9728bb899
|
Update eynollah.py
predict quietly please
|
2 years ago |
Robert Sachunsky
|
fb6d97091b
|
OCR-D wrapper: expose tables param
|
2 years ago |
|
Robert Sachunsky
|
1ac0a7e06f
|
try loading as TF SavedModel instead of HDF5
|
2 years ago |
|
Robert Sachunsky
|
73057d57d1
|
silentium!
|
2 years ago |
|
cneud
|
3d54719c87
|
fix import
|
2 years ago |
|
cneud
|
58ca226f2d
|
apply some fixes from main
|
2 years ago |
Konstantin Baierer
|
6c8f60993f
|
Merge branch 'main' into 420-namespace-package
|
2 years ago |
|
Konstantin Baierer
|
ea792d1e4a
|
📦 v0.2.0
|
2 years ago |
|
Konstantin Baierer
|
8e894e5b7b
|
Merge remote-tracking branch 'bertsky/savedmodel-format'
|
2 years ago |
|
Konstantin Baierer
|
7cd07dd550
|
use PEP420 style qurator namespace
|
2 years ago |
|
Konstantin Baierer
|
71d0ec8dfe
|
📦 v0.1.0
|
2 years ago |
|
Robert Sachunsky
|
875e4fe32b
|
log number of detected regions
|
2 years ago |
|
Robert Sachunsky
|
318ea6acca
|
OCR-D wrapper: expose tables param
|
2 years ago |
|
Robert Sachunsky
|
23f0c0b40a
|
ocrd-tool: replace by persistent model URL
|
2 years ago |
|
Robert Sachunsky
|
5c26bdf402
|
ocrd-tool: add model archive to resmgr resources
|
2 years ago |
|
Robert Sachunsky
|
7345f6bf67
|
remove TF1 session and GC controls, avoid repeating load_model
|
2 years ago |
|
Robert Sachunsky
|
a56988a35a
|
contours: numpy now needs dtype=object
|
2 years ago |
|
Robert Sachunsky
|
2d9ccac354
|
contours: simplify
|
2 years ago |
|
Robert Sachunsky
|
ab4bb7cd7b
|
silentium!
|
2 years ago |
|
Robert Sachunsky
|
79e897d3b2
|
try loading as TF SavedModel instead of HDF5
|
2 years ago |
|
vahid
|
38bf0d8740
|
solving issue by loading model by directory as input
|
2 years ago |
|
vahid
|
583cdcee2c
|
new (hybrid cnn+transformer) textline model which can accelerate to extract contour textlines faster
|
2 years ago |
|
vahid
|
8d5079c909
|
issue #77 is resolved on main branch
|
2 years ago |
|
vahid
|
402c5339ac
|
issue #77 is resolved
|
2 years ago |
|
vahid
|
01bfc3914d
|
extracting page as an option
|
3 years ago |
|
vahidrezanezhad
|
ae7c424889
|
Update eynollah.py
|
3 years ago |
|
vahid
|
cd9920eea7
|
extracting page
|
3 years ago |
|
vahid
|
735abc43f3
|
option to ignore page extraction
|
3 years ago |
cneud
|
934bbd5892
|
cleanup
|
3 years ago |
|
cneud
|
ecf117ca95
|
adapt to tf1.compat session mode in tf2
|
3 years ago |
|
Clemens Neudecker
|
568391ec4a
|
require model command line option (fix #59) (#73)
|
3 years ago |
|
vahid
|
3bbbeecfec
|
all options are enabled for light version
|
3 years ago |
 Gerber, Mike
|
f27ac155ae
|
🧹 Downgrade "Patch size" log message to debug
Fixes gh-55.
|
3 years ago |
|
vahid
|
adf10942fa
|
issue #55 resolved
|
3 years ago |
|
vahid
|
2eacb9a8ec
|
renaming the models
|
3 years ago |
|
vahid
|
c606391c31
|
flow from directory
|
3 years ago |