Skip to content

added cristae model and single channel transfrom #100

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Feb 28, 2025
Merged

added cristae model and single channel transfrom #100

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
466c733
added cristae model and single channel transfrom
lufre1 Feb 21, 2025
4334d7d
modified normalization function so it handles different channel sizes
lufre1 Feb 27, 2025
3cfeda4
changed to torch_em standardize
lufre1 Feb 28, 2025
f033882
removed debug relic
lufre1 Feb 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion synapse_net/inference/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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

Expand All @@ -25,6 +26,7 @@ def _get_model_registry():
"compartments": "527983720f9eb215c45c4f4493851fd6551810361eda7b79f185a0d304274ee1",
"mitochondria": "24625018a5968b36f39fa9d73b121a32e8f66d0f2c0540d3df2e1e39b3d58186",
"mitochondria2": "553decafaff4838fff6cc8347f22c8db3dee5bcbeffc34ffaec152f8449af673",
"cristae": "f96c90484f4ea92ac0515a06e389cc117580f02c2aacdc44b5828820cf38c3c3",
"ribbon": "7c947f0ddfabe51a41d9d05c0a6ca7d6b238f43df2af8fffed5552d09bb075a9",
"vesicles_2d": "eb0b74f7000a0e6a25b626078e76a9452019f2d1ea6cf2033073656f4f055df1",
"vesicles_3d": "b329ec1f57f305099c984fbb3d7f6ae4b0ff51ec2fa0fa586df52dad6b84cf29",
Expand All @@ -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",
Expand Down Expand Up @@ -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
2 changes: 1 addition & 1 deletion synapse_net/inference/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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)
Copy link
Contributor

@constantinpape constantinpape Feb 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here you assume that we never want to normalize the first channel, and you assume that we always have only two channels. I don't think we should make such a general assumption.

else:
input_volume = torch_em.transform.raw.standardize(input_volume)

Expand Down
3 changes: 3 additions & 0 deletions synapse_net/tools/segmentation_widget.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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(
Expand Down