wreal_mask is blank

[sjh0923]

Hi there,
Your software is very good. It solves a lot of problems.But I'm having problems with it.
The files generated during the run are blank.

from pathlib import Path
dataset_directory = Path("/home/sangjh/softwaredata/CryoVesNet/test")
pl = cryovesnet.Pipeline(dataset_directory,pattern="*.rec.nad")
CryoVesNet Pipeline: the pipeline is created for /home/sangjh/softwaredata/CryoVesNet/test
*.rec.nad
Pixel size: 0.9616000175476074
pl.setup_cryovesnet_dir(make_masks=False)
CryoVesNet Pipeline: setting up cryovesnet directory
/home/sangjh/softwaredata/CryoVesNet/test/cryovesnet
pl.run_deep(force_run=True)
Rescale Factor: 0.4370909170670943
2025-03-11 04:46:10.253792: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-03-11 04:46:10.572123: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory
2025-03-11 04:46:10.572157: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1850] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
CryoVesNet pipeline: Running unet segmentation if there are less than 4 file in ./deep directory
2025-03-11 04:46:11.238057: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
(?, 32, 32, 32, 1)
5
ROI: 24
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [04:38<00:00, 27.83s/it]
(219, 448, 448)
(219, 448, 448)
pl.rescale(force_run=True,slice_range=None)
CryoVesNet Pipeline: zooming the unet mask
(500, 1024, 1024)
last output array name: deep_mask
last mrc file saved : cryovesnet/sjht0255_9.62Apx.rec_zoomed_mask.mrc
pl.label_vesicles(within_segmentation_region = False)
CryoVesNet Pipeline: running label_vesicles
finding global threshold on unet mask: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [02:09<00:00, 6.49s/it]
Threshold: 0.8
last output array name: deep_labels
last mrc file saved : cryovesnet/sjht0255_9.62Apx.rec_deep_labels.mrc
pl.label_vesicles_adaptive(separating =True)
CryoVesNet Pipeline: running label_vesicles_adaptive
Tabel computed!
Collision vesicles:
Empty DataFrame
Columns: [label, area, centroid-0, centroid-1, centroid-2, bbox-0, bbox-1, bbox-2, bbox-3, bbox-4, bbox-5, extent, area_zscore, extent_zscore]
Index: []
Tabel computed!
Vesicles to remove:
Empty DataFrame
Columns: [area, centroid-0, centroid-1, centroid-2, bbox-0, bbox-1, bbox-2, bbox-3, bbox-4, bbox-5, extent, area_zscore, extent_zscore]
Index: []
Tabel computed!
last output array name: clean_deep_labels
last mrc file saved : cryovesnet/sjht0255_9.62Apx.rec_clean_deep_labels.mrc
(Empty DataFrame
Columns: [label, area, centroid-0, centroid-1, centroid-2, bbox-0, bbox-1, bbox-2, bbox-3, bbox-4, bbox-5, extent, area_zscore, extent_zscore]
Index: [], Empty DataFrame
Columns: [area, centroid-0, centroid-1, centroid-2, bbox-0, bbox-1, bbox-2, bbox-3, bbox-4, bbox-5, extent, area_zscore, extent_zscore]
Index: [])
pl.make_spheres(keep_ellipsoid = True)
CryoVesNet Pipeline: Making vesicles spherical.
fitting sphere to vesicles: 0it [00:00, ?it/s]
Identify the ellipsoid vesicles: 0it [00:00, ?it/s]
0
0
last output array name: sphere_labels
last mrc file saved : cryovesnet/sjht0255_9.62Apx.rec_sphere.mrc
Empty DataFrame
Columns: [thickness, density, radius, center, corr, mahalanobis, p, radials]
Index: []
pl.repair_spheres()
CryoVesNet Pipeline: Repairing vesicles.
Warning: cytomask is not set. Surrounding labels are not removed.
Traceback (most recent call last):
File "", line 1, in
File "/home/sangjh/softwaredata/CryoVesNet/cryovesnet/pipeline.py", line 669, in repair_spheres
temp = cryovesnet.adjacent_vesicles(sphere_df)
File "/home/sangjh/softwaredata/CryoVesNet/cryovesnet/cryovesnet.py", line 891, in adjacent_vesicles
dm = distance_matrix(new_centroids, new_centroids)
File "/data/biosoftware/miniconda3/miniconda3/envs/CryoVesNet/lib/python3.9/site-packages/scipy/spatial/_kdtree.py", line 902, in distance_matrix
m, k = x.shape
ValueError: not enough values to unpack (expected 2, got 1)

When I open wreal_mask.tiff with napari, it's blank.And When I run pl.repair_spheres(), I also get an error, which I think may be caused by the procedure file not printing the correct content.

The MRC file was generated through the processing of a TIFF file by Warp and denoised by CryoCARE.

Did I miss something when following your protocols?Or did I do something wrong?

Thanks in advance
Sandy

[amineuron]

Hi Sandy,

Thanks for the detailed report! It looks like the issue may stem from an empty mask, causing subsequent steps to operate on null data. You might want to check the MRC file header using IMOD's header command to ensure the format is correct (e.g., float32 vs. int16).

If the mask appears blank in Napari, that could indicate a problem in an earlier step. If your files are in float32, try converting them to int16. You can also generate 16-bit MRC files directly in WARP by setting the appropriate flag.

Let me know if this helps!

Best,
Amin

[sjh0923]

Hi Amin,
Thanks for your quick response.
I used IMOD to convert the MRC file, but the result is still blank.And the result of the code is exactly the same as before. Could it be an issue with my data itself? Most of my data consists of irregular spherical shapes—could that be the reason?

This is my data.

Did I miss something?
Best,
Sandy