mirror of
https://github.com/mikegerber/ocrd_calamari.git
synced 2025-06-26 03:59:53 +02:00
👷🏾♂️ Use gt4histocr-calamari1/ as directory name for the Calmari 1 model
This commit is contained in:
parent
0a9dbd0c25
commit
0e59c2317a
3 changed files with 11 additions and 11 deletions
12
Makefile
12
Makefile
|
@ -11,7 +11,7 @@ help:
|
|||
@echo " Targets"
|
||||
@echo ""
|
||||
@echo " install Install ocrd_calamari"
|
||||
@echo " gt4histocr-calamari Get GT4HistOCR Calamari model (from SBB)"
|
||||
@echo " gt4histocr-calamari1 Get GT4HistOCR Calamari model (from SBB)"
|
||||
@echo " actevedef_718448162 Download example data"
|
||||
@echo " deps-test Install testing python deps via pip"
|
||||
@echo " repo/assets Clone OCR-D/assets to ./repo/assets"
|
||||
|
@ -34,9 +34,9 @@ install:
|
|||
|
||||
|
||||
# Get GT4HistOCR Calamari model (from SBB)
|
||||
gt4histocr-calamari:
|
||||
mkdir gt4histocr-calamari
|
||||
cd gt4histocr-calamari && \
|
||||
gt4histocr-calamari1:
|
||||
mkdir -p gt4histocr-calamari1
|
||||
cd gt4histocr-calamari1 && \
|
||||
wget https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz && \
|
||||
tar xfv model.tar.xz && \
|
||||
rm model.tar.xz
|
||||
|
@ -73,12 +73,12 @@ assets-clean:
|
|||
rm -rf test/assets
|
||||
|
||||
# Run unit tests
|
||||
test: test/assets gt4histocr-calamari
|
||||
test: test/assets gt4histocr-calamari1
|
||||
# declare -p HTTP_PROXY
|
||||
$(PYTHON) -m pytest --continue-on-collection-errors test $(PYTEST_ARGS)
|
||||
|
||||
# Run unit tests and determine test coverage
|
||||
coverage: test/assets gt4histocr-calamari
|
||||
coverage: test/assets gt4histocr-calamari1
|
||||
coverage erase
|
||||
make test PYTHON="coverage run"
|
||||
coverage report
|
||||
|
|
|
@ -41,8 +41,8 @@ pip install .
|
|||
Download models trained on GT4HistOCR data:
|
||||
|
||||
```
|
||||
make gt4histocr-calamari
|
||||
ls gt4histocr-calamari
|
||||
make gt4histocr-calamari1
|
||||
ls gt4histocr-calamari1
|
||||
```
|
||||
|
||||
## Example Usage
|
||||
|
@ -50,7 +50,7 @@ Before using `ocrd-calamari-recognize` get some example data and model, and
|
|||
prepare the document for OCR:
|
||||
```
|
||||
# Download model and example data
|
||||
make gt4histocr-calamari
|
||||
make gt4histocr-calamari1
|
||||
make actevedef_718448162
|
||||
|
||||
# Create binarized images and line segmentation using other OCR-D projects
|
||||
|
@ -62,7 +62,7 @@ ocrd-tesserocr-segment-line -I OCR-D-SEG-REGION -O OCR-D-SEG-LINE
|
|||
|
||||
Finally recognize the text using ocrd_calamari and the downloaded model:
|
||||
```
|
||||
ocrd-calamari-recognize -p '{ "checkpoint": "../gt4histocr-calamari/*.ckpt.json" }' -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI
|
||||
ocrd-calamari-recognize -p '{ "checkpoint": "../gt4histocr-calamari1/*.ckpt.json" }' -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI
|
||||
```
|
||||
|
||||
You may want to have a look at the [ocrd-tool.json](ocrd_calamari/ocrd-tool.json) descriptions
|
||||
|
|
|
@ -14,7 +14,7 @@ from .base import assets
|
|||
|
||||
METS_KANT = assets.url_of('kant_aufklaerung_1784-page-region-line-word_glyph/data/mets.xml')
|
||||
WORKSPACE_DIR = '/tmp/test-ocrd-calamari'
|
||||
CHECKPOINT = os.path.join(os.getcwd(), 'gt4histocr-calamari/*.ckpt.json')
|
||||
CHECKPOINT = os.path.join(os.getcwd(), 'gt4histocr-calamari1/*.ckpt.json')
|
||||
|
||||
# Because XML namespace versions are so much fun, we not only use one, we use TWO!
|
||||
NSMAP = { "pc": "http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15" }
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue