qurator-spk/ocrd_calamari
1
0
Fork 0
mirror of https://github.com/mikegerber/ocrd_calamari.git synced 2025-07-25 18:09:54 +02:00
Code Releases Activity

init from constructor not process(), use conventional name setup()

Browse source
This commit is contained in:
Robert Sachunsky 2021-06-26 13:50:00 +02:00
parent da98713e73
commit 3bde7cb37f
1 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
ocrd_calamari/recognize.py
View file

@ -39,9 +39,14 @@ class CalamariRecognize(Processor):
kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL] kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL]
kwargs['version'] = '%s (calamari %s, tensorflow %s)' % (OCRD_TOOL['version'], calamari_version, tensorflow_version) kwargs['version'] = '%s (calamari %s, tensorflow %s)' % (OCRD_TOOL['version'], calamari_version, tensorflow_version)
super(CalamariRecognize, self).__init__(*args, **kwargs) super(CalamariRecognize, self).__init__(*args, **kwargs)
if hasattr(self, 'output_file_grp'):
# processing context
self.setup()
def _init_calamari(self): def setup(self):
"""
Set up the model prior to processing.
"""
if not self.parameter.get('checkpoint', None) and self.parameter.get('checkpoint_dir', None): if not self.parameter.get('checkpoint', None) and self.parameter.get('checkpoint_dir', None):
resolved = self.resolve_resource(self.parameter['checkpoint_dir']) resolved = self.resolve_resource(self.parameter['checkpoint_dir'])
self.parameter['checkpoint'] = '%s/*.ckpt.json' % resolved self.parameter['checkpoint'] = '%s/*.ckpt.json' % resolved
@ -69,8 +74,6 @@ class CalamariRecognize(Processor):
assert_file_grp_cardinality(self.input_file_grp, 1) assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1) assert_file_grp_cardinality(self.output_file_grp, 1)
self._init_calamari()
for (n, input_file) in enumerate(self.input_files): for (n, input_file) in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID page_id = input_file.pageId or input_file.ID
log.info("INPUT FILE %i / %s", n, page_id) log.info("INPUT FILE %i / %s", n, page_id)