added cristae model and single channel transfrom

Author: lufre1

synapse_net/inference/inference.py

@@ -10,6 +10,7 @@
 from .mitochondria import segment_mitochondria
 from .ribbon_synapse import segment_ribbon_synapse_structures
 from .vesicles import segment_vesicles
+from .cristae import segment_cristae
 from .util import get_device
 from ..file_utils import get_cache_dir
 
@@ -25,6 +26,7 @@ def _get_model_registry():
         "compartments": "527983720f9eb215c45c4f4493851fd6551810361eda7b79f185a0d304274ee1",
         "mitochondria": "24625018a5968b36f39fa9d73b121a32e8f66d0f2c0540d3df2e1e39b3d58186",
         "mitochondria2": "553decafaff4838fff6cc8347f22c8db3dee5bcbeffc34ffaec152f8449af673",
+        "cristae": "f96c90484f4ea92ac0515a06e389cc117580f02c2aacdc44b5828820cf38c3c3",
         "ribbon": "7c947f0ddfabe51a41d9d05c0a6ca7d6b238f43df2af8fffed5552d09bb075a9",
         "vesicles_2d": "eb0b74f7000a0e6a25b626078e76a9452019f2d1ea6cf2033073656f4f055df1",
         "vesicles_3d": "b329ec1f57f305099c984fbb3d7f6ae4b0ff51ec2fa0fa586df52dad6b84cf29",
@@ -35,6 +37,7 @@ def _get_model_registry():
         "compartments": "https://owncloud.gwdg.de/index.php/s/DnFDeTmDDmZrDDX/download",
         "mitochondria": "https://owncloud.gwdg.de/index.php/s/1T542uvzfuruahD/download",
         "mitochondria2": "https://owncloud.gwdg.de/index.php/s/GZghrXagc54FFXd/download",
+        "cristae": "https://owncloud.gwdg.de/index.php/s/Df7OUOyQ1Kc2eEO/download",
         "ribbon": "https://owncloud.gwdg.de/index.php/s/S3b5l0liPP1XPYA/download",
         "vesicles_2d": "https://owncloud.gwdg.de/index.php/s/d72QIvdX6LsgXip/download",
         "vesicles_3d": "https://owncloud.gwdg.de/index.php/s/A425mkAOSqePDhx/download",
@@ -214,14 +217,16 @@ def run_segmentation(
     """
     if model_type.startswith("vesicles"):
         segmentation = segment_vesicles(image, model=model, tiling=tiling, scale=scale, verbose=verbose, **kwargs)
-    elif model_type == "mitochondria":
+    elif model_type == "mitochondria" or model_type == "mitochondria2":
         segmentation = segment_mitochondria(image, model=model, tiling=tiling, scale=scale, verbose=verbose, **kwargs)
     elif model_type == "active_zone":
         segmentation = segment_active_zone(image, model=model, tiling=tiling, scale=scale, verbose=verbose, **kwargs)
     elif model_type == "compartments":
         segmentation = segment_compartments(image, model=model, tiling=tiling, scale=scale, verbose=verbose, **kwargs)
     elif model_type == "ribbon":
         segmentation = _segment_ribbon_AZ(image, model=model, tiling=tiling, scale=scale, verbose=verbose, **kwargs)
+    elif model_type == "cristae":
+        segmentation = segment_cristae(image, model=model, tiling=tiling, scale=scale, verbose=verbose, **kwargs)
     else:
         raise ValueError(f"Unknown model type: {model_type}")
     return segmentation

synapse_net/inference/util.py

@@ -121,7 +121,7 @@ def get_prediction(
     # If we have channels then the standardization is done independently per channel.
     if with_channels:
         # TODO Check that this is the correct axis.
-        input_volume = torch_em.transform.raw.standardize(input_volume, axis=(1, 2, 3))
+        input_volume = np.stack([torch_em.transform.raw.normalize(input_volume[0]), input_volume[1]], axis=0)
     else:
         input_volume = torch_em.transform.raw.standardize(input_volume)
 

synapse_net/tools/segmentation_widget.py

@@ -178,6 +178,9 @@ def on_predict(self):
         if model_type == "ribbon":  # Currently only the ribbon model needs the extra seg.
             extra_seg = self._get_layer_selector_data(self.extra_seg_selector_name)
             kwargs = {"extra_segmentation": extra_seg}
+        elif model_type == "cristae":  # Cristae model expects 2 3D volumes
+            image = np.stack([image, self._get_layer_selector_data(self.extra_seg_selector_name)], axis=0)
+            kwargs = {}
         else:
             kwargs = {}
         segmentation = run_segmentation(