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

🚧 Add a. our augmented GT4HistOCR Calamari model b. chreul's GT4HistOCR model

Browse source
This commit is contained in:
Gerber, Mike 2020-11-30 17:52:24 +01:00
parent 04d16d93d0
commit 42e8bf67e2
3 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
Dockerfile-ocrd_calamari
View file

@ -14,7 +14,9 @@ RUN ${PIP_INSTALL} \
# Copy OCR models # Copy OCR models
RUN mkdir -p /var/lib/calamari-models/GT4HistOCR RUN mkdir -p /var/lib/calamari-models/GT4HistOCR
COPY data/calamari-models/GT4HistOCR/2019-12-11T11_10+0100 /var/lib/calamari-models/GT4HistOCR/2019-12-11T11_10+0100 COPY data/calamari-models/GT4HistOCR/2019-12-11T11_10+0100 /var/lib/calamari-models/GT4HistOCR/2019-12-11T11_10+0100
# XXX experimental
COPY data/calamari-models/GT4HistOCR/2019-12-18T17_24+0100-with-augmentation-UNTESTED /var/lib/calamari-models/GT4HistOCR/2019-12-18T17_24+0100
COPY data/mirror/github.com/Calamari-OCR/calamari_models/gt4histocr /var/lib/calamari-models/GT4HistOCR-chreul
# Check pip dependencies # Check pip dependencies

2
build
View file

@ -8,6 +8,8 @@ DATA_SUBDIR=data
get_from_annex() { get_from_annex() {
annex_get 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200/*.ckpt*' annex_get 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200/*.ckpt*'
annex_get 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100/*.ckpt*' annex_get 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100/*.ckpt*'
annex_get 'calamari-models/GT4HistOCR/2019-12-18T17_24+0100*/*.ckpt*'
annex_get 'mirror/github.com/Calamari-OCR/calamari_models/gt4histocr/*.ckpt*'
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'

2
data

@ -1 +1 @@
Subproject commit bd1628e1aefbb0766655ee3726b4b0234d20a4f1 Subproject commit 3fbdbcf368f05ea76253d6d3327644c4d755d6f8