ilastik plugin for napari

    Napari plugin for interactive pixel classification. Designed to be similar to the pixel classification workflow in classic ilastik.


    Currently, this plugin requires you to use a conda environment. If you haven't used conda before, please read conda user guide.

    Instad of the default miniconda installation, we highly recommend to use mambaforge. It has better default settings, and the mamba command, which is an (almost) drop-in replacement for conda.

    After installing mambaforge, create a new environment with this plugin installed:

    mamba create -y -c ilastik-forge -n my-napari-env napari-ilastik

    Finally, launch napari in the new environment.

    conda activate my-napari-env

    Napari Hub and pip

    You can also install this plugin via Napari Hub or pip. However, in this case you must do that inside a conda environment with the fastfilters package installed:

    mamba create -y -c ilastik-forge -n my-napari-env fastfilters
    conda activate my-napari-env
    pip install ilastik-napari


    As a prerequisite, make sure you understand the napari basics.

    1. Open your image, or use a sample in File - Open Sample.

      Use a sample image

    2. Activate the plugin in the Plugins menu.

      Activate the plugin

    3. In layer list, create a new Labels layer.

      Labels layer

    4. In layers control, switch to the paint action.

      Paint action

    5. Draw your background labels.

      Paint the background

    6. Switch to a new label.

      Switch label

    7. Draw your foreground labels.

      Paint cells

    8. Select output types you need, and click Run.

      Plugin interface

    9. The plugin will create one layer for each output type, which you save as normal napari layers.

      Example output


    Create a development environment:

    mamba create -y -n ilastik-napari-dev -c ilastik-forge fastfilters setuptools-scm conda-build anaconda-client
    conda activate napari-ilastik-dev
    pip install -e .

    Build conda package:

    conda activate napari-ilastik-dev
    mamba build -c ilastik-forge conda-recipe
    anaconda upload /path/to/the/new/package.tar.bz2

    Build wheel and sdist packages:

    conda activate napari-ilastik-dev
    pip install build twine
    python -m build
    python -m twine upload --repository testpypi dist/*


    • 0.2.1

    Last updated:

    • 28 February 2023

    First released:

    • 28 February 2023


    • MIT

    Supported data:

    • Information not submitted

    Plugin type:

    • Information not submitted

    GitHub activity:

    • Stars: 12
    • Forks: 1
    • Issues + PRs: 7

    Python versions supported:

    Operating system:


    • napari[all]
    • numpy (>=1.20)
    • qtpy
    • scikit-learn
    • sparse

    Sign up to receive updates