diff --git a/requirements.txt b/requirements.txt index 6b012f7..85fd500 100644 --- a/requirements.txt +++ b/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 diff --git a/sbb_binarize/ocrd_cli.py b/sbb_binarize/ocrd_cli.py index 7d9a7d5..34f16b3 100644 --- a/sbb_binarize/ocrd_cli.py +++ b/sbb_binarize/ocrd_cli.py @@ -40,15 +40,17 @@ 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(): - raise FileNotFoundError("Does not exist or is not a directory: %s" % model_path) + if not model_path.is_dir(): + raise FileNotFoundError("Does not exist or is not a directory: %s" % model_path) kwargs['parameter']['model'] = str(model_path) super().__init__(*args, **kwargs) @@ -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):