Nagini3D Napari

A simple plugin that implements Nagini3D inference tools 3D biological segmentation.

  • Quentin RAPILLY

License GNU GPL v3.0 PyPI Python Version tests codecov napari hub npe2 Copier

A simple plugin that implements Nagini3D inference tools for segmenting 3D biological images.


This napari plugin was generated with copier using the napari-plugin-template (None).

Installation

You can install nagini3d-napari via pip:

pip install nagini3d-napari

If napari is not already installed, you can install nagini3d-napari with napari and Qt via:

pip install "nagini3d-napari[all]"

Installation advice

We recommend installing our plugin on a clean Python environment (Python 3.9 to 3.11 prefered), to avoid any conflict with other packages.

  • Create and activate the environment with:
python -m venv <path-to-new-virtual-environment>
source <path-to-new-virtual-environment>/bin/activate
  • Download the package in the new env with
pip install "nagini3d-napari[all]"
  • Launch Napari
napari
  • Activate NAGINI3D in the plugin manager.

Models weights and testing images

An archive containing model weigths trained on different datasets and testing images are available on zenodo at https://zenodo.org/records/17909858.

Documentation

The GitHub project containing all the documentation is available at https://github.com/QuentinRapilly/NAGINI-3D.

Contributing

Contributions are very welcome. Tests can be run with tox, please ensure the coverage at least stays the same before you submit a pull request.

License

Distributed under the terms of the GNU GPL v3.0 license, "nagini3d-napari" is free and open source software

Issues

If you encounter any problems, please file an issue along with a detailed description.

Version:

  • 0.2.1

Last updated:

  • 2026-03-26

First released:

  • 2025-12-08

License:

  • GNU GENERAL PUBLIC LICENSE ...

Supported data:

  • Information not submitted

Plugin type:

Open extension:

Save extension:

Python versions supported:

Operating system:

  • Information not submitted

Requirements:

  • numpy
  • magicgui
  • qtpy
  • scikit-image
  • scikit-learn
  • torch==2.1.0
  • torchvision==0.16.0
  • nagini3d==0.2.3
  • napari[all]; extra == "all"
Website by the napari team, original design by CZI. Go to napari main website.