def raw2seg(config):
input_paths = load_paths(config)
gui_logger.info(f"Running the pipeline on: {input_paths}")
gui_logger.info("Executing pipeline, see terminal for verbose logs.")
all_pipeline_steps = [('preprocessing', configure_preprocessing_step),
('cnn_prediction', configure_cnn_step),
('cnn_postprocessing',
configure_cnn_postprocessing_step),
('segmentation', configure_segmentation_step),
('segmentation_postprocessing',
configure_segmentation_postprocessing_step)]
for pipeline_step_name, pipeline_step_setup in all_pipeline_steps:
gui_logger.info(
f"Executing pipeline step: '{pipeline_step_name}'. Parameters: '{config[pipeline_step_name]}'. Files {input_paths}."
)
pipeline_step = pipeline_step_setup(input_paths,
config[pipeline_step_name])
output_paths = pipeline_step()
# replace input_paths for all pipeline steps except DataPostProcessing3D
if not isinstance(pipeline_step, DataPostProcessing3D):
input_paths = output_paths
gui_logger.info(f"Pipeline execution finished!")
def __init__(self,
predictions_paths,
nuclei_predictions_path,
save_directory="LiftedMulticut",
beta=0.6,
run_ws=True,
ws_2D=True,
ws_threshold=0.4,
ws_minsize=50,
ws_sigma=2.0,
ws_w_sigma=0,
post_minsize=50,
n_threads=6,
state=True,
**kwargs):
super().__init__(input_paths=predictions_paths,
save_directory=save_directory,
file_suffix='_lmc',
state=state)
self.nuclei_predictions_paths = load_paths(nuclei_predictions_path)
self.beta = beta
# Watershed parameters
self.run_ws = run_ws
self.ws_2D = ws_2D
self.ws_threshold = ws_threshold
self.ws_minsize = ws_minsize
self.ws_sigma = ws_sigma
self.ws_w_sigma = ws_w_sigma
# Post processing size threshold
self.post_minsize = post_minsize
# Multithread
self.n_threads = n_threads