[NEW!] A graphical user interface (GUI) is now available, in its alpha version! Launch it with the
deformetrica guicommand. We warmly welcome any feedback about this new feature.
The Deformetrica applications are called with command lines of the form:
deformetrica estimate model.xml data_set.xml [-p optimization_parameters.xml]or
deformetrica compute model.xml [-p optimization_parameters.xml]
deformetricais an alias for
python deformetrica.py: the main script of the software, in the
srcfolder, automatically created during the conda installation.
model.xmlis an xml file containing the description of the task that is to be performed (such as estimating a registration, an atlas, ...) as well as some hyper-parameters for the objects and the deformations used.
data_set.xmlis an xml file containing the paths to the input objects from which a statistical model will be estimated. The shooting and parallel transport applications are direct computations, and do not need this xml file.
optimization_parameters.xmlcontains optional details about the optimization method.
Additional arguments in the command line are:
--output=path/to/output/folderused to specify the output directory i.e. where all results are saved.
-v DEBUG: allow to get more printed information about the current computation.
Tutorials and examples are available to demonstrate how the three xml files should be filled. Exhaustive lists of options are given in the user manual.
The Deformetrica applications theoretically rely on a control-points-based instance of the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework. Find more details on the dedicated wiki page.
- The LDDMM framework: a description of the mathematics behind Deformetrica.
- Tutorials and examples for each functionality:
- User manual: