I would like to train a model for supervised classification; however, I am receiving a "Domain is empty" error message as I attempt to train a model. I don't know what I am doing wrong. I don't have any samples, but I was able to train a model from importing vector layers in past eCog projects. I don't understand why it wouldn't work now.


  • Matthias Staengel


    Please first have a look at this supervised classification tutorial.

    Please also have a look at this example project on supervised classification.

    The error "Domain is empty" means, that the process does not find any objects based on the domain definitions. This could be the "Level", "Class filter", "Condition", etc.. It actually can be seen as a "filtering" of objects that the process should consider.

    If no objects are found based on these filter definitions (AND condition) you will get this error "Domain is empty". If you receive this error message (don't panic!) you will need to check the domain parameters and make sure that there are objects that the algorithm can work with.


  • Matthias Staengel

    Based on your question, I have put together a FAQ. I think a lot of users will find this highly helpful.
    Thank you for your question!

Recent Discussions

Need more help?

Enter Knowledge Base Contact Support