Samia Mohinta

Hi! I was facing the same issue, where the generated network architecture file was not a pdf. I fixed it by replacing _optimize_trace with _optimize_graph inside pytorch_builder.py [Line 71] file...

Hi @hep-raidium, Do you know which torch version you are using? Also do you have torchvision installed? > Hi, > > I had the same issue and dealt with it...

Hi @FabianIsensee, [Pull request](https://github.com/MIC-DKFZ/nnUNet/pull/1408) submitted with the fixes.

Hi Tom, Data is here: gs://zlatic-lab/SAM_3G/clahe/ You can load it in neuroglancer. Info is here: ``` "@type": "neuroglancer_multiscale_volume", "data_type": "uint8", "num_channels": 1, "scales": [ { "chunk_sizes": [ [ 64, 64,...

Hi Tom, I realized the error is actually because the tiny window (attached pic) at the bottom right is blank: The volume loads now, but the navigation is off and...

We have a separate requirement re. serving this volume from a local SSD. Do you think that is possible? Because pointing it to the gs:// bucket is slow. If I...

Sure, data is [here](https://www.dropbox.com/scl/fo/gl8y4nrkx2um2klfi40qc/AHsn-1Enkol6yyiatKTrweQ?rlkey=kh6lupwavzpfu3i2a76cb54w6&st=p9e2i0ro&dl=0). I am running it as such: ```python n [1]: import cc3d ...: import numpy as np In [2]: import zarr In [3]: f = zarr.open("/media/samia/DATA/ark/connexion/data/MITO-HEMI/data_3d/merged/hemi_x11051_y20992_z21948_merged_ids_clahed.zarr") In...

Hi William, Many thanks! You were right about the version, I had to upgrade to the latest version (3.17) and then it seems to be working. Closing the issue now....

Thank you so much @bdpedigo! This has worked :)

Hi @bdpedigo , Is it possible to do the opposite? Given a root_id find all node locations in space (volume) that belong to that root_id? Currently, I can perform `mesh.get(root_id)`...