Merge pull request #25 from OCR-D/resolve-resources

processor: self.resolve_resource model in addition to SBB_BINARIZE_DATA

.circleci/config.yml

@@ -9,14 +9,13 @@ jobs:
       - checkout
       - restore_cache:
           keys:
-            - model-cache
+            - ocrd-resources-{{ checksum "requirements.txt" }}-{{ checksum "Makefile" }}
+      - run: make install
       - run: make model
       - save_cache:
-          key: model-cache
+          key: ocrd-resources-{{ checksum "requirements.txt" }}-{{ checksum "Makefile" }}
           paths:
-            models.tar.gz
+            ocrd-resources
-            models
-      - run: make install
       - run: git submodule update --init
       - run: make test
 
@@ -27,14 +26,13 @@ jobs:
       - checkout
       - restore_cache:
           keys:
-            - model-cache
+            - ocrd-resources-{{ checksum "requirements.txt" }}-{{ checksum "Makefile" }}
+      - run: make install
       - run: make model
       - save_cache:
-          key: model-cache
+          key: ocrd-resources-{{ checksum "requirements.txt" }}-{{ checksum "Makefile" }}
           paths:
-            models.tar.gz
+            ocrd-resources
-            models
-      - run: make install
       - run: git submodule update --init
       - run: make test
 

Makefile

@@ -1,6 +1,3 @@
-# Directory to store models
-MODEL_DIR = $(PWD)/models
-
 # BEGIN-EVAL makefile-parser --make-help Makefile
 
 help:
@@ -22,15 +19,11 @@ install:
 	pip install .
 
 # Downloads the pre-trained models from qurator-data.de
-model: $(MODEL_DIR)/model1_bin.h5
+.PHONY: model
-
+model:
-$(MODEL_DIR)/model1_bin.h5: models.tar.gz
+	ocrd resmgr download --allow-uninstalled --location cwd ocrd-sbb-binarize default
-	tar xf models.tar.gz
-
-models.tar.gz:
-	wget 'https://qurator-data.de/sbb_binarization/models.tar.gz'
 
 # Run tests
 test: model
-	cd repo/assets/data/kant_aufklaerung_1784/data; ocrd-sbb-binarize -I OCR-D-IMG -O BIN -P model $(MODEL_DIR)
+	ocrd-sbb-binarize -m repo/assets/data/kant_aufklaerung_1784/data/mets.xml -I OCR-D-IMG -O BIN -P model default
-	cd repo/assets/data/kant_aufklaerung_1784-page-region/data; ocrd-sbb-binarize -I OCR-D-IMG -O BIN -P model $(MODEL_DIR) -P level-of-operation region
+	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

requirements.txt

@@ -1,7 +1,7 @@
 numpy >= 1.17.0, < 1.19.0
 setuptools >= 41
 opencv-python-headless
-ocrd >= 2.18.0
+ocrd >= 2.22.3
 keras >= 2.3.1, < 2.4
 h5py < 3
 tensorflow-gpu >= 1.15, < 1.16

sbb_binarize/ocrd_cli.py

@@ -40,11 +40,13 @@ class SbbBinarizeProcessor(Processor):
         kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL]
         kwargs['version'] = OCRD_TOOL['version']
         if not(kwargs.get('show_help', None) or kwargs.get('dump_json', None) or kwargs.get('show_version')):
+            LOG = getLogger('processor.SbbBinarize.__init__')
             if not 'model' in kwargs['parameter']:
                 raise ValueError("'model' parameter is required")
             model_path = Path(kwargs['parameter']['model'])
             if not model_path.is_absolute():
-                if 'SBB_BINARIZE_DATA' in environ:
+                if 'SBB_BINARIZE_DATA' in environ and environ['SBB_BINARIZE_DATA']:
+                    LOG.info("Environment variable SBB_BINARIZE_DATA is set to '%s' - prepending to model value '%s'. If you don't want this mechanism, unset the SBB_BINARIZE_DATA environment variable.", environ['SBB_BINARIZE_DATA'], model_path)
                     model_path = Path(environ['SBB_BINARIZE_DATA']).joinpath(model_path)
                     model_path = model_path.resolve()
                     if not model_path.is_dir():
@@ -61,7 +63,7 @@ class SbbBinarizeProcessor(Processor):
         assert_file_grp_cardinality(self.output_file_grp, 1)
 
         oplevel = self.parameter['operation_level']
-        model_path = self.parameter['model'] # pylint: disable=attribute-defined-outside-init
+        model_path = self.resolve_resource(self.parameter['model'])
         binarizer = SbbBinarizer(model_dir=model_path, logger=LOG)
 
         for n, input_file in enumerate(self.input_files):