Split some HDF5 into util module

extensions/chaeo/examples/transfer_labels_to_ilastik_object_classifier.py

@@ -8,41 +8,11 @@ import skimage
 import uuid
 
 from extensions.chaeo.accessors import MonoPatchStackFromFile
+from extensions.chaeo.h5util import get_dataset_info
 from extensions.chaeo.models import PatchStackObjectClassifier
 from model_server.accessors import generate_file_accessor, GenericImageDataAccessor, write_accessor_data_to_file
 
 
-def get_dataset_info(h5: h5py.File, lane : int = 0):
-    """
-    Report out specific datasets in ilastik project file HDF5
-    :param h5: handle to ilastik project file, as h5py.File object
-    :param lane: ilastik lane identifier
-    :return: (dict) selected data values from project file
-    """
-    lns = f'{lane:04d}'
-    lane = f'Input Data/infos/lane{lns}'
-    info = {}
-    for gk in ['Raw Data', 'Segmentation Image']:
-        info[gk] = {}
-        for dk in ['location', 'filePath', 'shape', 'nickname']:
-            try:
-                info[gk][dk] = h5[f'{lane}/{gk}/{dk}'][()]
-            except Exception as e:
-                print(e)
-        try:
-            info[gk]['id'] = uuid.UUID(h5[f'{lane}/{gk}/datasetId'][()].decode())
-        except ValueError as e:
-            info[gk]['id'] = '<invalid UUID>'
-        info[gk]['axistags'] = json.loads(h5[f'{lane}/{gk}/axistags'][()].decode())
-        info[gk]['axes'] = [ax['key'] for ax in info[gk]['axistags']['axes']]
-
-    obj_cl_group = h5[f'ObjectClassification/LabelInputs/{lns}']
-    info['misc'] = {
-        'number_of_label_inputs': len(obj_cl_group.items())
-    }
-    return info
-
-
 def generate_ilastik_object_classifier(
         template_ilp: str,
         where: str,
@@ -180,15 +150,16 @@ def compare_object_maps(truth: GenericImageDataAccessor, inferred: GenericImageD
 if __name__ == '__main__':
     root =  Path('c:/Users/rhodes/projects/proj0011-plankton-seg/')
     template_ilp = root / 'exp0014/template_obj.ilp'
-    where_patch_stack = root / 'exp0009/output/labeled_patches-20231018-0006'
+    where_patch_stack = root / 'exp0009/output/labeled_patches-20231030-0001'
 
     # auto-populate an object classifier
-    auto_ilp = generate_ilastik_object_classifier(
-        template_ilp,
-        where_patch_stack,
-        stack_name='train',
-        proj_name='auto_obj_before'
-    )
+    # auto_ilp = generate_ilastik_object_classifier(
+    #     template_ilp,
+    #     where_patch_stack,
+    #     stack_name='train',
+    #     proj_name='auto_obj_before'
+    # )
+    auto_ilp = 'auto_obj_before.ilp'
 
     def infer_and_compare_training_set(ilp, suffix):
         # infer object labels from the same data used to train the classifier

extensions/chaeo/h5util.py

+import json
+import uuid
+
+import h5py
+
+def get_dataset_info(h5: h5py.File, lane : int = 0):
+    """
+    Report out specific datasets in ilastik project file HDF5
+    :param h5: handle to ilastik project file, as h5py.File object
+    :param lane: ilastik lane identifier
+    :return: (dict) selected data values from project file
+    """
+    lns = f'{lane:04d}'
+    lane = f'Input Data/infos/lane{lns}'
+    info = {}
+    for gk in ['Raw Data', 'Segmentation Image']:
+        info[gk] = {}
+        for dk in ['location', 'filePath', 'shape', 'nickname']:
+            try:
+                info[gk][dk] = h5[f'{lane}/{gk}/{dk}'][()]
+            except Exception as e:
+                print(e)
+        try:
+            info[gk]['id'] = uuid.UUID(h5[f'{lane}/{gk}/datasetId'][()].decode())
+        except ValueError as e:
+            info[gk]['id'] = '<invalid UUID>'
+        info[gk]['axistags'] = json.loads(h5[f'{lane}/{gk}/axistags'][()].decode())
+        info[gk]['axes'] = [ax['key'] for ax in info[gk]['axistags']['axes']]
+
+    obj_cl_group = h5[f'ObjectClassification/LabelInputs/{lns}']
+    info['misc'] = {
+        'number_of_label_inputs': len(obj_cl_group.items())
+    }
+    return info
\ No newline at end of file