A Napari plugin, part of AI OnDemand, to provide an accessible interface for running deep learning models on images via our Nextflow pipeline.
This [napari] plugin was generated with [Cookiecutter] using [@napari]'s [cookiecutter-napari-plugin] template.
You can install this plugin using pip, either from the repo directly:
pip install git+https://github.com/FrancisCrickInstitute/ai-on-demand.git
or clone and install locally:
git clone https://github.com/FrancisCrickInstitute/ai-on-demand.git
cd ai-on-demand
pip install .
We have provided a conda environment file to install all the dependencies for this plugin. To install the environment, run the following command:
conda env create -f ai-od.yml
Note that when it comes to the installation of napari this may be preferable, depending on whether your system is best supported by the pip- or conda-packaged version.
If you have any issues installing Napari, see their installation guide. Then, you can reinstall this package following the instructions above.
This plugin makes a call to Nextflow when running the pipeline. To install Nextflow, see their installation guide.
If you have any issues with that, there is a version of Nextflow in bioconda that you can use instead, but it may not be the most up-to-date version.
For general usage of the plugin, see the user guide here.
For developers, see our developer guide for some tips on how to get started and contribute to the plugin.
For more information on the AI OnDemand project, see our wiki.
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.
Currently GPL-3.0 licensed. See LICENSE for more information. Pending further discussion.
If you encounter any problems, please raise an issue along with a detailed description.