Pixel Classification XGBoost

A plugin for pixel classification using XGBoost, inspired by Digital Sreeni's Youtube video.

Note: This plugin is work-in-progress. Check out the github issues to see what's currently being worked on.

Usage¶

Load an example image into napari. Add a Labels layer by clicking on this button:

Then, draw a sparse annotation on the image. Try to draw thin lines on background and foreground, e.g. like this:

Then click the menu Layers > Segment > Train Pixel Classifier (XGBoost).

In the dialog, select the original image and the labels layer. Also enter a filename where the model should be saved. Afterwards, click on Run to explore the result.

Installation¶

You can install napari-xgboost via pip:

pip install napari-xgboost

To install latest development version :

pip install git+https://github.com/haesleinhuepf/napari-xgboost.git

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 BSD-3 license, "napari-xgboost" is free and open source software

Issues¶

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