Commit Graph

106 Commits (ef3fb44fb528e9e52b78fe1e787e38142da7a7d4)
 

Author SHA1 Message Date
Gerber, Mike ef3fb44fb5 Allow controlling of output hierarchy level, e.g. only line, not words+glyphs
Gerber, Mike 0f0bae18ba Remove GT text to not accidently check it instead of OCR text
Gerber, Mike 82fe0333f1 Test word segmentation (Fixes )
Gerber, Mike 9010250911 ♻ test: Move binarization into the workspace fixture
Gerber, Mike 6f4736f8e4 Do word segmentation as expected by OCR-D PAGE specs
Gerber, Mike 0f9c94e7dc 🐛 Start with TextEquiv index=1 to adhere to OCR-D PAGE conventions
https://ocr-d.github.io/page#multiple-textequivs
Gerber, Mike 909632493b 🚧 Add future TODOs
Gerber, Mike 3149e1d9e0 📝 unwanted()
Gerber, Mike 91cca1e1b8 📝 Document why we are using Unicode text segmentation to produce word results
Gerber, Mike 0a572df0ba 📝 README: Add information about the new glyph and word segmentation
Gerber, Mike 2650189910 🧹 Add whitespace
Gerber, Mike f75426060e 🧹 Remove debugging print
Gerber, Mike decaa7b69f 🎨 Use polygon_from_x0y0x1y1 to build word/glyph polygon
Gerber, Mike 2ccfc7b195 🎨 Set vim textwidth
Gerber, Mike 507bc1ce5e Include proper word + glyph segmentation
Gerber, Mike 24532f693a 🚧 Use character positions as word segmentation
Gerber, Mike 17dbeb2480 🔧 Loosen tensorflow-gpu dependency a bit to 1.15.*
Gerber, Mike c416e0c253 Revert "🐛 Use the documented package name for TensorFlow 1.15.x"
This reverts commit 739f43e9da.
Gerber, Mike 5dfd809fbc 🐛 CircleCI: Try upgrading pip
Gerber, Mike 7d02c8dff0 📝 README-DEV: Document installing test requirements
Gerber, Mike 739f43e9da 🐛 Use the documented package name for TensorFlow 1.15.x
dependabot[bot] c09fe169f2
Bump tensorflow-gpu from 1.14.0 to 1.15.2
Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.14.0 to 1.15.2.
- [Release notes](https://github.com/tensorflow/tensorflow/releases)
- [Changelog](https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md)
- [Commits](https://github.com/tensorflow/tensorflow/compare/v1.14.0...v1.15.2)

Signed-off-by: dependabot[bot] <support@github.com>
Mike Gerber c9cf782dbf
Merge pull request from OCR-D/fix-circle
circle: set locale to a UTF-8 variant so python doesn't fall back to ascii
Konstantin Baierer 60aa158341 circle: set locale to a UTF-8 variant so python doesn't fall back to ascii
Gerber, Mike 1c36265599 ⬆ Update ocrd
Gerber, Mike 2797b0e806 CircleCI: Try to fix encoding problem
Gerber, Mike e8f60f9bf4 CircleCI: Try to fix encoding problem
Gerber, Mike 7bdd15648f CircleCI: Try to fix encoding problem
Gerber, Mike d2ca24bf1e CircleCI: Try to fix encoding problem
Gerber, Mike 357a2a970a ⬆ Update model download URL
Gerber, Mike 49b6dfe735 🧹 Clean up trailing whitespace
Gerber, Mike 95281f3d29 Add metadata about the recognition operation w/ parameter info
Gerber, Mike dc38f0ee51 🎨 Use TOOL constant convention from the other OCR-D processors
Gerber, Mike b8129c6425 🧹 Do not advertise and support untested models
Gerber, Mike 5273247ab3 Remove broken __main__ handling (stick to pytest)
Gerber, Mike e1b9d381a0 Actually binarize the image (not grayscale!)
Gerber, Mike e07b333db1 Convert to a pytest style test
Gerber, Mike 2393edc645 CircleCI: Install imagemagick
Gerber, Mike 99d04ddccb Fix tests by 1. binarizing and 2. use the GT4HistOCR model
Gerber, Mike 2aff9d8a48 🔧 Add PyCharm project files
Gerber, Mike 71a0a32ebf 🧹 Tests: Reduce useless warning messages a bit
Robert Sachunsky 103b1d7671 remove existing annotation below the line level to avoid inconsistency
Mike Gerber 2f87ae662d
Migrate TODO to issue
Mike Gerber fa6db585e3
Migrate extended prediction data TODO to issue
Gerber, Mike 830a61c2fe 📝 README: Add testing instructions + reference README-DEV.md
Gerber, Mike 93de16d81e 📝 Makefile: Remove redundant comments for the variables
Gerber, Mike 40316904d4 🐛 Makefile: Fix "make test"
Gerber, Mike c46b719c3d 🐛 Makefile: Fix "make test"
Gerber, Mike c1b83a707b 🐛 Makefile: Fix it...
Mike Gerber 8bea30a051
Merge pull request from OCR-D/doc
README/Makefile: installation and models