Quick Start¶
Technical Issues
The renaming process is ongoing, and you might encounter technical issues
The new conda-forge package is not yet released, until then the in-app update does not work.
Issues with the windows installer have been resolved.
If you encounter issues, please use PlantSeg <= 2.0.0rc14 for now, thank you!
PanSeg has two main modes of operation: interactively, using the Napari viewer, or for batch processing from the command line. The following sections will guide you through the installation and usage of PanSeg in each of these modes.
Interactive PanSeg with Napari Viewer¶
After installing PanSeg using the installer, there should
be a start menu entry to launch PanSeg.
Alternatively, launch panseg --napari in the terminal.
Using the GUI, you can
- load and view images
- apply pre- and post-processing steps and directly see the results
- perform segmentation
- interactively proofread segmentations
- save the processing history as repeatable workflows
- train custom boundary prediction models
Details to the GUI workflow and its sections can be found in the GUI documentation.
Run batch workflows¶
PlanSeg can apply a set of operations (a workflow) to a batch of images.
To generate a batch workflow, you need to create a workflow yaml file.
While you process a single image, all steps are recorded.
Once you have saved the resulting image, you can save the recording as a workflow
file to be applied to many images.
Before you can run the batch workflow, you need to set the correct paths to the files
you want to process, and where you want the results to be saved.
PanSeg provides an editor for this; start it from the Output tab, or by running:
panseg --edit [workflow.yaml]
Once the correct input/output paths are set, you can run the workflow:
panseg --config [workflow.yaml]