qurator-spk/sbb_binarization
1
0
Fork 0
mirror of https://github.com/qurator-spk/sbb_binarization.git synced 2025-07-25 18:59:52 +02:00
Code Issues Releases Wiki Activity

improve/update tests

Browse source
This commit is contained in:
Robert Sachunsky 2023-04-12 22:55:12 +02:00
parent 8a12d40769
commit 5b1634d6b3
2 changed files with 48 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

32
Makefile
View file

@ -1,16 +1,17 @@
# BEGIN-EVAL makefile-parser --make-help Makefile # BEGIN-EVAL makefile-parser --make-help Makefile
.PHONY: help install
help: help:
@echo "" @echo ""
@echo " Targets" @echo " Targets"
@echo "" @echo ""
@echo " install Install with pip" @echo " install Install with pip"
@echo " model Downloads the pre-trained models from qurator-data.de" @echo " models Downloads the pre-trained models from qurator-data.de"
@echo " test Run tests" @echo " test Run tests"
@echo " clean Remove copies/results in test/assets"
@echo "" @echo ""
@echo " Variables" @echo " Variables"
@echo "" @echo ""
@echo " MODEL_DIR Directory to store models"
# END-EVAL # END-EVAL
@ -19,11 +20,26 @@ install:
pip install . pip install .
# Downloads the pre-trained models from qurator-data.de # Downloads the pre-trained models from qurator-data.de
.PHONY: model .PHONY: models
model: models:
ocrd resmgr download --allow-uninstalled --location cwd ocrd-sbb-binarize default ocrd resmgr download ocrd-sbb-binarize "*"
repo/assets:
git submodule update --init repo/assets
# Setup test data
test/assets: repo/assets
@mkdir -p $@
cp -r -t $@ repo/assets/data/*
# Run tests # Run tests
test: model .PHONY: test
ocrd-sbb-binarize -m repo/assets/data/kant_aufklaerung_1784/data/mets.xml -I OCR-D-IMG -O BIN -P model default test: test/assets models
ocrd-sbb-binarize -m repo/assets/data/kant_aufklaerung_1784-page-region/data/mets.xml -I OCR-D-IMG -O BIN -P model default -P operation_level region ocrd-sbb-binarize -m test/assets/kant_aufklaerung_1784/data/mets.xml -I OCR-D-IMG -O BIN -P model default
ocrd-sbb-binarize -m test/assets/kant_aufklaerung_1784/data/mets.xml -I OCR-D-IMG -O BIN2 -P model default-2021-03-09
ocrd-sbb-binarize -m test/assets/kant_aufklaerung_1784-page-region/data/mets.xml -g phys_0001 -I OCR-D-GT-SEG-REGION -O BIN -P model default -P operation_level region
ocrd-sbb-binarize -m test/assets/kant_aufklaerung_1784-page-region/data/mets.xml -g phys_0001 -I OCR-D-GT-SEG-REGION -O BIN2 -P model default-2021-03-09 -P operation_level region
.PHONY: clean
clean:
-$(RM) -fr test/assets

32
README.md
View file

@ -18,7 +18,7 @@ Clone the repository, enter it and run
### Models ### Models
Pre-trained models in `HDF5` format can be downloaded from here: Pre-trained models in HDF5 format can be downloaded from here:
https://qurator-data.de/sbb_binarization/ https://qurator-data.de/sbb_binarization/
@ -26,6 +26,11 @@ We also provide a Tensorflow `saved_model` via Huggingface:
https://huggingface.co/SBB/sbb_binarization https://huggingface.co/SBB/sbb_binarization
With [OCR-D](https://ocr-d.de/), you can use the [Resource Manager](Tensorflow SavedModel) to deploy models, e.g.
ocrd resmgr download ocrd-sbb-binarize "*"
## Usage ## Usage
```sh ```sh
@ -39,11 +44,22 @@ Images containing a lot of border noise (black pixels) should be cropped beforeh
### Example ### Example
```sh
sbb_binarize -m /path/to/model/ myimage.tif myimage-bin.tif
```
To use the [OCR-D](https://ocr-d.de/) interface: sbb_binarize -m /path/to/model/ myimage.tif myimage-bin.tif
```sh
ocrd-sbb-binarize --overwrite -I INPUT_FILE_GRP -O OCR-D-IMG-BIN -P model "/var/lib/sbb_binarization"
``` To use the [OCR-D](https://ocr-d.de/en/spec/cli) interface:
ocrd-sbb-binarize -I INPUT_FILE_GRP -O OCR-D-IMG-BIN -P model default
## Testing
For simple smoke tests, the following will
- download models
- download test data
- run the OCR-D wrapper (on page and region level):
make model
make test