andreasmang / claire Goto Github PK
View Code? Open in Web Editor NEWConstrained Large Deformation Diffeomorphic Image Registration (CLAIRE)
License: GNU General Public License v3.0
Constrained Large Deformation Diffeomorphic Image Registration (CLAIRE)
License: GNU General Public License v3.0
Dear Claire developers,
Thank you for open sourcing this great package. I would like to ask you, if you have solution to adopt this package to python env. ?
Second question is related to data size, Is this package able of handling data larger than RAM size? Like data with size of terabyte.
when using "h1s-stokes" like
./bin/claire -mr ./doc/data/brain01.nii.gz -mt ./doc/data/brain02.nii.gz -regnorm h1s-stokes
return CUDA error string: an illegal memory access was encountered
CUDA error code src/Spectral/mpicufft.cpp:276: 700
other parameters works well
gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
nvcc Build cuda_11.0_bu.TC445_37.28540450_0
petsc 3.14.2
openmpi mpirun (Open MPI) 4.0.3
Hi CLAIRE Team,
I hope this message finds you well.
First, thank you for your fantastic work on CLAIRE. I read your manuscript with great interest and I’m genuinely excited to use it in our research with total-body PET. It's not every day someone casually drops a diffeomorphic tool, with heavy parallelization/optimization in mind.
However, I’ve been struggling with the installation process. Despite following the instructions carefully, I’ve run into several issues that I haven’t been able to resolve. This has made it difficult for me to get CLAIRE up and running.
I believe an official Docker image for CLAIRE could make the installation much more straightforward. It would help not only me but also others who might be facing similar challenges. I considered creating a Docker image myself to contribute back, but my difficulties with the initial setup have prevented me from doing so.
Would you consider providing a Docker image for CLAIRE? I think it would be a great help to many in the community. If there’s any way I can assist in this process, please let me know.
Thank you for your time and consideration.
Cheers,
Lalith
original post can be found here: #9 (comment)
The link to the libmorton library is broken (at least in the cpu branch).
wget https://www.math.uh.edu/~andreas/resources/clairelibs/morton.tar.gz
PNETCDF support for multi-GPU code needs to be added (for large-scale applications)
I am trying to install Claire on ubuntu 20.04 and am unable to compile.
Error 1:
petscmat.h:685:1: error: ‘PETSC_CXX_INLINE’ does not name a type; did you mean ‘PETSC_C_INLINE’?
685 | PETSC_STATIC_INLINE PetscErrorCode MatGetValue(Mat v,PetscInt i,PetscInt j,PetscScalar *va) {return MatGetValues(v,1,&i,1,&j,va);}
Error 2:
./include/MemoryUtils.hpp: In member function ‘PetscErrorCode reg::ManagedMemory::CopyDeviceToHost()’:
./include/MemoryUtils.hpp:260:3: error: ‘PETSC_FUNCTION_NAME_CXX’ was not declared in this scope; did you mean ‘PETSC_FUNCTION_NAME_C’?
260 | PetscFunctionBegin;
Has anyone else seen these there is a huge barrage of these errors I just selected one instance.
Best,
Ahsan
Hi @andreasmang, what are the contributing guidelines for this project? They are missing from the repository.
I have been unable to install a working copy of claire-gpu. The installation
initially appeared to have completed successfully up until running the makefile:
make -j
The terminal output begins with the message:
fatal: not a git repository (or any of the parent directories): .git
and continues. The next error message is
./include/ReadWriteReg.hpp:29:10: fatal error: pnetcdf.h: No such file or directory
29 | #include "pnetcdf.h"
| ^~~~~~~~~~~
compilation terminated.
Several similar messages appear refering to pnetcdf.h. Working backwards, I
found that that the compilation process ran into a compilation error:
Error during compile, check cxx_opt_sgl/lib/petsc/conf/make.log
Send it and cxx_opt_sgl/lib/petsc/conf/configure.log to [email protected]
The two files in question are included. Note that all dependencies were downloaded/installed using the provided build scipt and all paths have been set.
Thank you for any help you can provide.
Tom
Hi @andreasmang, how you have tested/validated your code and it's outputs? Currently, as far as I can find, there is no automated test suite via Github Actions or other.
the build script for external libraries fails for directories with spaces in the name
I am wondering if Claire has a docker file and if not, are you planning to release one?
@andreasmang:
I am hoping that you can help me with the installation of CLAIRE. Any advice would be very welcome and appreciated. I have performed the following steps. Thanks @tjasaki
Installed Nvidia CUDA Toolkit.
Graphics Card: NVIDIA Corporation TU117GLM [Quadro T2000 Mobile / Max-Q] / Quadro T2000/PCIe/SSE2.
Processor: Intel® Core™ i9-9880H CPU @ 2.30GHz × 16.
OS: Ubuntu 20.04.2 LTS.
cmake, niftilib, python all operational
Installed mpich 3.3.2-2build1 (Ubuntu) (MPI-3.1 standard)
mpicc, mpicxx, and nvcc all recognized, with directories
/usr/bin/mpicc
/usr/bin/mpicxx
/usr/bin/nvcc
running make from claire-gpu/deps results in the following message:
Unable to find cuda in default locations!
Perhaps you can specify with --with-cuda-dir=
If you do not want cuda, then give --with-cuda=0
Changing makefile with "WITH_CUDA_MPI = no" results in the same message.
Changing makefile with "WITH_CUDA_MPI = no" and "BUILD_GPU = no" results in a completed make.
Moving forward with this configuration, I set the environment variables using: source env_source.sh
I modified the top-level makefile to specify "BUILD_GPU = no" and "WITH_CUDA_MPI = no". Executing :make -j" results in the error mesage
config.mk:68: *** This branch only supports GPU build. Stop.
I reverted back to "BUILD_GPU = yes". Running "make VERBOSE=1 VVERBOSE=1 config" shows the following:
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.