def __init__(self, shell, headless, workflow_cmdline_args,
project_creation_args, *args, **kwargs):
graph = kwargs.pop("graph") if "graph" in kwargs else Graph()
super().__init__(shell,
headless,
workflow_cmdline_args,
project_creation_args,
graph=graph,
*args,
**kwargs)
self.stored_object_classifier = None
# Parse workflow-specific command-line args
parser = argparse.ArgumentParser()
parser.add_argument(
"--fillmissing",
help="use 'fill missing' applet with chosen detection method",
choices=["classic", "svm", "none"],
default="none",
)
parser.add_argument("--nobatch",
help="do not append batch applets",
action="store_true",
default=False)
parsed_creation_args, unused_args = parser.parse_known_args(
project_creation_args)
self.fillMissing = parsed_creation_args.fillmissing
parsed_args, unused_args = parser.parse_known_args(
workflow_cmdline_args)
if parsed_args.fillmissing != "none" and parsed_creation_args.fillmissing != parsed_args.fillmissing:
logger.error(
"Ignoring --fillmissing cmdline arg. Can't specify a different fillmissing setting after the project has already been created."
)
self.batch = not parsed_args.nobatch
self._applets = []
self.createInputApplets()
if self.fillMissing != "none":
self.fillMissingSlicesApplet = FillMissingSlicesApplet(
self, "Fill Missing Slices", "Fill Missing Slices",
self.fillMissing)
self._applets.append(self.fillMissingSlicesApplet)
# our main applets
self.objectExtractionApplet = ObjectExtractionApplet(
workflow=self, name="Object Feature Selection")
self.objectClassificationApplet = ObjectClassificationApplet(
workflow=self)
self._tableExporter = TableExporter(
self.objectClassificationApplet.topLevelOperator)
self.dataExportApplet = ObjectClassificationDataExportApplet(
self,
"Object Information Export",
table_exporter=self._tableExporter)
# Customization hooks
self.dataExportApplet.prepare_for_entire_export = self.prepare_for_entire_export
self.dataExportApplet.post_process_entire_export = self.post_process_entire_export
opDataExport = self.dataExportApplet.topLevelOperator
opDataExport.WorkingDirectory.connect(
self.dataSelectionApplet.topLevelOperator.WorkingDirectory)
opDataExport.SelectionNames.setValue(
self.ExportNames.asDisplayNameList())
self._batch_export_args = None
self._batch_input_args = None
self._export_args = None
self.batchProcessingApplet = None
self._applets.append(self.objectExtractionApplet)
self._applets.append(self.objectClassificationApplet)
self._applets.append(self.dataExportApplet)
if self.batch:
self.batchProcessingApplet = BatchProcessingApplet(
self, "Batch Processing", self.dataSelectionApplet,
self.dataExportApplet)
self._applets.append(self.batchProcessingApplet)
if unused_args:
exportsArgParser, _ = self.exportsArgParser
self._export_args, unused_args = exportsArgParser.parse_known_args(
unused_args)
# We parse the export setting args first. All remaining args are considered input files by the input applet.
self._batch_export_args, unused_args = self.dataExportApplet.parse_known_cmdline_args(
unused_args)
self._batch_input_args, unused_args = self.batchProcessingApplet.parse_known_cmdline_args(
unused_args)
# For backwards compatibility, translate these special args into the standard syntax
self._batch_input_args.export_source = self._export_args.export_source
self.blockwiseObjectClassificationApplet = BlockwiseObjectClassificationApplet(
self, "Blockwise Object Classification",
"Blockwise Object Classification")
self._applets.append(self.blockwiseObjectClassificationApplet)
if unused_args:
logger.warning("Unused command-line args: {}".format(unused_args))
def __init__(self, shell, headless, workflow_cmdline_args,
project_creation_args, *args, **kwargs):
graph = kwargs['graph'] if 'graph' in kwargs else Graph()
if 'graph' in kwargs:
del kwargs['graph']
super(ObjectClassificationWorkflow,
self).__init__(shell,
headless,
workflow_cmdline_args,
project_creation_args,
graph=graph,
*args,
**kwargs)
self.stored_pixel_classifier = None
self.stored_object_classifier = None
# Parse workflow-specific command-line args
parser = argparse.ArgumentParser()
parser.add_argument(
'--fillmissing',
help="use 'fill missing' applet with chosen detection method",
choices=['classic', 'svm', 'none'],
default='none')
parser.add_argument('--filter',
help="pixel feature filter implementation.",
choices=['Original', 'Refactored', 'Interpolated'],
default='Original')
parser.add_argument('--nobatch',
help="do not append batch applets",
action='store_true',
default=False)
parsed_creation_args, unused_args = parser.parse_known_args(
project_creation_args)
self.fillMissing = parsed_creation_args.fillmissing
self.filter_implementation = parsed_creation_args.filter
parsed_args, unused_args = parser.parse_known_args(
workflow_cmdline_args)
if parsed_args.fillmissing != 'none' and parsed_creation_args.fillmissing != parsed_args.fillmissing:
logger.error(
"Ignoring --fillmissing cmdline arg. Can't specify a different fillmissing setting after the project has already been created."
)
if parsed_args.filter != 'Original' and parsed_creation_args.filter != parsed_args.filter:
logger.error(
"Ignoring --filter cmdline arg. Can't specify a different filter setting after the project has already been created."
)
self.batch = not parsed_args.nobatch
self._applets = []
self.pcApplet = None
self.projectMetadataApplet = ProjectMetadataApplet()
self._applets.append(self.projectMetadataApplet)
self.setupInputs()
if self.fillMissing != 'none':
self.fillMissingSlicesApplet = FillMissingSlicesApplet(
self, "Fill Missing Slices", "Fill Missing Slices",
self.fillMissing)
self._applets.append(self.fillMissingSlicesApplet)
if isinstance(self, ObjectClassificationWorkflowPixel):
self.input_types = 'raw'
elif isinstance(self, ObjectClassificationWorkflowBinary):
self.input_types = 'raw+binary'
elif isinstance(self, ObjectClassificationWorkflowPrediction):
self.input_types = 'raw+pmaps'
# our main applets
self.objectExtractionApplet = ObjectExtractionApplet(
workflow=self, name="Object Feature Selection")
self.objectClassificationApplet = ObjectClassificationApplet(
workflow=self)
self.dataExportApplet = ObjectClassificationDataExportApplet(
self, "Object Information Export")
self.dataExportApplet.set_exporting_operator(
self.objectClassificationApplet.topLevelOperator)
# Customization hooks
self.dataExportApplet.prepare_for_entire_export = self.prepare_for_entire_export
#self.dataExportApplet.prepare_lane_for_export = self.prepare_lane_for_export
self.dataExportApplet.post_process_lane_export = self.post_process_lane_export
self.dataExportApplet.post_process_entire_export = self.post_process_entire_export
opDataExport = self.dataExportApplet.topLevelOperator
opDataExport.WorkingDirectory.connect(
self.dataSelectionApplet.topLevelOperator.WorkingDirectory)
# See EXPORT_SELECTION_PREDICTIONS and EXPORT_SELECTION_PROBABILITIES, above
export_selection_names = [
'Object Predictions', 'Object Probabilities',
'Blockwise Object Predictions', 'Blockwise Object Probabilities'
]
if self.input_types == 'raw':
# Re-configure to add the pixel probabilities option
# See EXPORT_SELECTION_PIXEL_PROBABILITIES, above
export_selection_names.append('Pixel Probabilities')
opDataExport.SelectionNames.setValue(export_selection_names)
self._batch_export_args = None
self._batch_input_args = None
self._export_args = None
self.batchProcessingApplet = None
if self.batch:
self.batchProcessingApplet = BatchProcessingApplet(
self, "Batch Processing", self.dataSelectionApplet,
self.dataExportApplet)
if unused_args:
# Additional export args (specific to the object classification workflow)
export_arg_parser = argparse.ArgumentParser()
export_arg_parser.add_argument(
"--table_filename",
help=
"The location to export the object feature/prediction CSV file.",
required=False)
export_arg_parser.add_argument(
"--export_object_prediction_img", action="store_true")
export_arg_parser.add_argument(
"--export_object_probability_img", action="store_true")
export_arg_parser.add_argument(
"--export_pixel_probability_img", action="store_true")
# TODO: Support this, too, someday?
#export_arg_parser.add_argument( "--export_object_label_img", action="store_true" )
self._export_args, unused_args = export_arg_parser.parse_known_args(
unused_args)
if self.input_types != 'raw' and self._export_args.export_pixel_probability_img:
raise RuntimeError("Invalid command-line argument: \n"\
"--export_pixel_probability_img' can only be used with the combined "\
"'Pixel Classification + Object Classification' workflow.")
if sum([
self._export_args.export_object_prediction_img,
self._export_args.export_object_probability_img,
self._export_args.export_pixel_probability_img
]) > 1:
raise RuntimeError(
"Invalid command-line arguments: Only one type classification output can be exported at a time."
)
# We parse the export setting args first. All remaining args are considered input files by the input applet.
self._batch_export_args, unused_args = self.dataExportApplet.parse_known_cmdline_args(
unused_args)
self._batch_input_args, unused_args = self.batchProcessingApplet.parse_known_cmdline_args(
unused_args)
# For backwards compatibility, translate these special args into the standard syntax
if self._export_args.export_object_prediction_img:
self._batch_input_args.export_source = "Object Predictions"
if self._export_args.export_object_probability_img:
self._batch_input_args.export_source = "Object Probabilities"
if self._export_args.export_pixel_probability_img:
self._batch_input_args.export_source = "Pixel Probabilities"
self.blockwiseObjectClassificationApplet = BlockwiseObjectClassificationApplet(
self, "Blockwise Object Classification",
"Blockwise Object Classification")
self._applets.append(self.objectExtractionApplet)
self._applets.append(self.objectClassificationApplet)
self._applets.append(self.dataExportApplet)
if self.batchProcessingApplet:
self._applets.append(self.batchProcessingApplet)
self._applets.append(self.blockwiseObjectClassificationApplet)
if unused_args:
logger.warn("Unused command-line args: {}".format(unused_args))