qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-06-09 22:59:53 +02:00
Code Issues Projects Releases Wiki Activity

⬆️ ocrd-galley: Update sbb_binarization (including the model)

Browse source
This commit is contained in:
Gerber, Mike 2021-04-19 20:57:57 +02:00
parent 7add6858fc
commit 19649aaf91
4 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
Dockerfile-sbb_binarization
View file

@ -2,7 +2,7 @@ ARG DRONE_COMMIT="latest"
FROM quratorspk/ocrd-galley-core-cuda10.0:$DRONE_COMMIT FROM quratorspk/ocrd-galley-core-cuda10.0:$DRONE_COMMIT
ARG PIP_INSTALL="pip install --no-cache-dir" ARG PIP_INSTALL="pip install --no-cache-dir"
ARG SBB_BINARIZATION_COMMIT="ea69494" ARG SBB_BINARIZATION_COMMIT="2c7cd84"
# Build pip installable stuff # Build pip installable stuff
@ -12,7 +12,7 @@ RUN ${PIP_INSTALL} \
# Copy models # Copy models
COPY data/sbb_binarization /var/lib/sbb_binarization COPY data/sbb_binarization/2021-03-09 /var/lib/sbb_binarization
# Check pip dependencies # Check pip dependencies

4
build
View file

@ -13,14 +13,14 @@ get_from_annex() {
annex_get 'tesseract-models/GT4HistOCR/*.traineddata' annex_get 'tesseract-models/GT4HistOCR/*.traineddata'
annex_get 'textline_detection/*.h5' annex_get 'textline_detection/*.h5'
annex_get 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' annex_get 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz'
annex_get 'sbb_binarization/*.h5' annex_get 'sbb_binarization/2021-03-09/*.h5'
} }
get_from_web() { get_from_web() {
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/model.tar.xz' 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200' download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/model.tar.xz' 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200'
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz' 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100' download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz' 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100'
download_to 'https://qurator-data.de/tesseract-models/GT4HistOCR/models.tar' 'tesseract-models/GT4HistOCR' download_to 'https://qurator-data.de/tesseract-models/GT4HistOCR/models.tar' 'tesseract-models/GT4HistOCR'
download_to 'https://qurator-data.de/sbb_textline_detector/models.tar.gz' 'textline_detection' download_to 'https://qurator-data.de/sbb_textline_detector/models.tar.gz' 'textline_detection'
download_to --strip-components 1 'https://qurator-data.de/sbb_binarization/models.tar.gz' 'sbb_binarization' download_to --strip-components 1 'https://qurator-data.de/sbb_binarization/2021-03-09/models.tar.gz' 'sbb_binarization/2021-03-09'
download_to --no-unpack 'https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' download_to --no-unpack 'https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz'
} }
. $self_dir/qurator_data_lib.sh . $self_dir/qurator_data_lib.sh

2
build-tmp-XXX
View file

@ -10,7 +10,7 @@ get_from_web() {
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz' 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100' download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz' 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100'
download_to 'https://qurator-data.de/tesseract-models/GT4HistOCR/models.tar' 'tesseract-models/GT4HistOCR' download_to 'https://qurator-data.de/tesseract-models/GT4HistOCR/models.tar' 'tesseract-models/GT4HistOCR'
download_to 'https://qurator-data.de/sbb_textline_detector/models.tar.gz' 'textline_detection' download_to 'https://qurator-data.de/sbb_textline_detector/models.tar.gz' 'textline_detection'
download_to --strip-components 1 'https://qurator-data.de/sbb_binarization/models.tar.gz' 'sbb_binarization' download_to --strip-components 1 'https://qurator-data.de/sbb_binarization/2021-03-09/models.tar.gz' 'sbb_binarization/2021-03-09'
download_to --no-unpack 'https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' download_to --no-unpack 'https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz'
} }
. $self_dir/qurator_data_lib.sh . $self_dir/qurator_data_lib.sh

2
data

@ -1 +1 @@
Subproject commit 3fbdbcf368f05ea76253d6d3327644c4d755d6f8 Subproject commit c67004ecfff404409a6c47b53088e8b7efadc85f