Commit Graph

419 Commits (0b350118470b40cf30eb32d40e22ed644c57a5a8)
 

Author SHA1 Message Date
cneud d21cc42d87 Update README.md
remove Python 3.6 from supported versions
cneud 2c13f1bddc Update README.md
cneud 4642ccb36d Update config.yml
cneud 27834ce33d update CI
cneud f37d324812 Use renamed models in SavedModel format
cneud 4276417938 Update README.md
cneud 4807be1b62 Update requirements.txt
Konstantin Baierer 6c8f60993f Merge branch 'main' into 420-namespace-package
Konstantin Baierer ea792d1e4a 📦 v0.2.0
Konstantin Baierer e167e0863d 📝 changelog
Konstantin Baierer 8e894e5b7b Merge remote-tracking branch 'bertsky/savedmodel-format'
Konstantin Baierer 7cd07dd550 use PEP420 style qurator namespace
Konstantin Baierer 71d0ec8dfe 📦 v0.1.0
Konstantin Baierer 31a2ec8fe6 📝 changelog
Robert Sachunsky 875e4fe32b log number of detected regions
Robert Sachunsky 318ea6acca OCR-D wrapper: expose tables param
Robert Sachunsky 23f0c0b40a ocrd-tool: replace by persistent model URL
Robert Sachunsky 5c26bdf402 ocrd-tool: add model archive to resmgr resources
Robert Sachunsky 7345f6bf67 remove TF1 session and GC controls, avoid repeating load_model
Robert Sachunsky a56988a35a contours: numpy now needs dtype=object
Clemens Neudecker 13bc2378d9
Update config.yml ()
* Update config.yml

enable CI for Python 3.8

* Update test-eynollah.yml

Use 3.7 for actions
Robert Sachunsky 2d9ccac354 contours: simplify
Robert Sachunsky ab4bb7cd7b silentium!
Robert Sachunsky 79e897d3b2 try loading as TF SavedModel instead of HDF5
vahidrezanezhad a6fe781033
Merge pull request from emresvd/patch-1
Update README.md
Clemens Neudecker ac69136e8f
Update config.yml ()
* Update config.yml

* Update config.yml
emresvd 98529d6325
Update README.md
Clemens Neudecker 30ef006dfd
Update README.md
Clarify CLI options
Clemens Neudecker 5ca857018b
Update README.md
Clemens Neudecker ffc7f82906
Update README.md
Clemens Neudecker b75d8afb1d
Update README.md
Clemens Neudecker 000402f0dc
Update README.md
vahid 38bf0d8740 solving issue by loading model by directory as input
vahid 89e58910aa new (hybrid cnn+transformer) textline model which can accelerate to extract contour textlines faster
vahid 583cdcee2c new (hybrid cnn+transformer) textline model which can accelerate to extract contour textlines faster
Clemens Neudecker 07fe0d827d
Update Makefile
Clemens Neudecker dbf91876e1
Adapt to new location of models
vahid 8d5079c909 issue is resolved on main branch
vahid 402c5339ac issue is resolved
vahid 01bfc3914d extracting page as an option
Clemens Neudecker 00be99d29b
add short section on supported Python, TF and CUDA versions
vahidrezanezhad ae7c424889
Update eynollah.py
vahid cd9920eea7 extracting page
Robert Sachunsky 34a061782c
depend on tensorflow instead of tensorflow-gpu ()
vahid 735abc43f3 option to ignore page extraction
vahidrezanezhad ae1990a48e
Merge pull request from cneud/main
Adapt to use tf1.compat session in tf2
cneud 934bbd5892 cleanup
cneud 8c11b2253d update requirements (use tf2)
cneud ecf117ca95 adapt to tf1.compat session mode in tf2
Clemens Neudecker 568391ec4a
require model command line option (fix ) ()