Latest ilastik stable release 1.3.2

Dearest ilastik users,

we are happy to have finalized the latest stable release: 1.3.2

some highlights include

  • New color way! :rainbow:
  • Image features: sigmas can be specified, 2D/3D filter selection
  • Training data no longer required for headless processing
  • Carving improvements: block-wise preprocessing, various improvements, fixes
  • Window-leveling available in most workflows
  • Various improvements and fixes to the object classification workflow
  • Two labels always added in Pixel and Object Classification
  • Fixed Fiji-MaMuT export plugin
  • Will even work on Halloween :partying_face:

Download links for your convenience:

please let us know what you think or if you encounter any unusual behavior.



I have just installed the new version and seem to have issues saving Autocontext projects… Ie either save a duplicate of an existing project, or modified version of it (eg one label removed).
I have this error in the log
QObject::connect: Cannot queue arguments of type ‘QVector’
(Make sure ‘QVector’ is registered using qRegisterMetaType().)
Any idea?
I didn’t have issues with version 1.3.2cr2 btw. I’m now on 1.3.2



Hey mcdormart,

I don’t think the QObject ... thingy is not related.

So, what actually happens if you click on safe? Nothing at all? Do you get a message?

I thought that was the message sorry.
No nothing happens I just get stuck with the wheel of death or all greyed out… It saves 312Mb quickly then gets stucks (at 14% progress now, at 85% before- whole project is 1.2Gb). I’ve left it overnight the other day, before I had to kill ilastik, same again, saved only 310Mb or so.

Mmm actually now I remember having the same issue before… And the way around it to simply copy paste the project in windows, rename then open in ilastik and then modify… Not sure why I can’t ‘Save As’ from ilastik.

Hey @mcdomart,

just to get this in a more reproducible form, I’ll summarize.

ilastik-version: 1.3.2
OS: Windows 10?
Workflow is Autocontex

What would you say are the steps to reproduce the problem?

  1. Load some data (2d? 3d?)
  2. Did you do any feature selection and training?
  3. At what point did you try to save?

We would appreciate you taking the time to add some additional information for us to be able to reproduce the problem.