Skip to content

TractSeg command fail due to Error #15 #289

@DarioSARACINO

Description

@DarioSARACINO

Hello TractSeg community,
I have just installed TractSeg following standard instruction of my Apple Silicon M4 machine with MacOS Sequoia 15.6.
I regularly installed dependencies before, including FSL, Python3, pytorch. As soon as I run TractSeg command I receive this error message:

OMP: Error #15: Initializing libomp.dylib, but found libomp.dylib already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://openmp.llvm.org/

This happens whatever the input is, also with TractSeg alone command. Instead, Tracking, Tractometry and calc_fa commands seem to work properly. I initially thought this was due to conflicting Python versions, so I removed 3.13 then 3.12, up to native 3.9 version, but it's still the same. I also uninstalled and re-installed main packages (numpy, scipy, scikit-learn) and nothing works. I tried to create a virtual environment with the variable indicated in the message, but the command crashes after loading weights. I read previous issues reporting similar problems, like #283 but I wasn't able to resolve the problem. Do you have any idea about how to fix it?
Thanks a lot in advance,
Dario

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions