Commit Graph

78 Commits (1621532092e796b9160b8214d325ed621e4453cb)

Author SHA1 Message Date
vahidrezanezhad 1621532092
Merge branch 'main' into eynollah_light 1 year ago
vahid d68f240b59 loading TensorFlow SavedModel format is now present 1 year ago
vahid 380f59ad67 let hybrid textline light model be loaded 1 year ago
vahidrezanezhad 29e6ad076f
renaming textline light model 1 year ago
Robert Sachunsky 529f2c0e19 set_memory_growth to all GPU devices alike 1 year ago
Robert Sachunsky 8fe3567123
set_memory_growth to all GPU devices alike 1 year ago
vahid d3735b12f4 pushing commits 2d9ccac and 7345f6b into eynollah_light 1 year ago
cneud 817e5a6af9 update docstring 1 year ago
cneud a9728bb899 Update eynollah.py
predict quietly please
1 year ago
Robert Sachunsky 1ac0a7e06f try loading as TF SavedModel instead of HDF5 1 year ago
Robert Sachunsky 73057d57d1 silentium! 1 year ago
cneud 3d54719c87 fix import 1 year ago
cneud 58ca226f2d apply some fixes from main 1 year ago
Robert Sachunsky 875e4fe32b log number of detected regions 1 year ago
Robert Sachunsky 7345f6bf67 remove TF1 session and GC controls, avoid repeating load_model 1 year ago
Robert Sachunsky a56988a35a contours: numpy now needs dtype=object 1 year ago
Robert Sachunsky 2d9ccac354 contours: simplify 1 year ago
Robert Sachunsky ab4bb7cd7b silentium! 1 year ago
Robert Sachunsky 79e897d3b2 try loading as TF SavedModel instead of HDF5 1 year 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 01bfc3914d extracting page as an option 2 years ago
vahidrezanezhad ae7c424889
Update eynollah.py 2 years ago
vahid cd9920eea7 extracting page 2 years ago
vahid 735abc43f3 option to ignore page extraction 2 years ago
cneud 934bbd5892 cleanup 2 years ago
cneud ecf117ca95 adapt to tf1.compat session mode in tf2 2 years ago
vahid 3bbbeecfec all options are enabled for light version 2 years ago
Gerber, Mike f27ac155ae 🧹 Downgrade "Patch size" log message to debug
Fixes gh-55.
2 years ago
vahid adf10942fa issue #55 resolved 2 years ago
vahid 2eacb9a8ec renaming the models 2 years ago
vahid c606391c31 flow from directory 2 years ago
vahid cf5ef8f5ae light version as option 2 years ago
vahidrezanezhad b8a532180a light version integration 2 years ago
vahidrezanezhad 10f1acef29
Merge pull request #65 from mikegerber/fix/enhanced-message
Fix/enhanced message
2 years ago
Gerber, Mike 1fe8f92afc 🐛 Clarify message if an image was enhanced 2 years ago
Gerber, Mike 7ccd7663e1 💄 Improve more timing messages 2 years ago
Gerber, Mike cdea0acffe 💄 Improve timing messages (Fixes #62) 2 years ago
vahidrezanezhad 169b50aaaf fixed: empty page error due None table contours 3 years ago
vahid 0859d22f4c modifications 3 years ago
vahid 14c588e162 resolving an issue 3 years ago
vahid 254abf4d3d more modifications for tables 3 years ago
vahid c67e155431 table detection completed, enhanced images can be now written to output 3 years ago
vahid a5c940705a tables are integrated 3 years ago
vahid 4560738427 #45 fixed 3 years ago
vahid d1330ffb80 #43 resolved 3 years ago
vahid 43c9302390 fixed #40 and separators are also written in xml 3 years ago
vahid 799a7c7632 fixed #38 3 years ago
vahid c4b2c71e68 resolving issue https://github.com/qurator-spk/eynollah/issues/38 3 years ago
vahid 7cbecadccc adding the binarization model and option to binarize input document for the cases like dark, stronly bright and other ones 3 years ago