RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation
This can be done by cloning the server source code again or installing with pip:
pip install root-painter-trainer==0.2.27.0
This is a work in progress release for development and testing purposes. The latest stable release is available here: https://github.com/Abe404/root_painter/releases/tag/0.2.25
The RhizoVision segmentation option included in this client also requires that you also update the server to the latest version. This can be done by cloning the server source code again or installing with pip:
pip install root-painter-trainer==0.2.25.1
Note this is no longer the latest release. Latest release available at: https://github.com/Abe404/root_painter/releases
In this release, predicted area, corrected area, and the difference between them (area error) are now available from the metrics plot, providing feedback on model performance in terms of under or over-estimation of area during interactive model training.
Full Changelog: https://github.com/Abe404/root_painter/compare/0.2.22...0.2.23
Fixed a bug that prevented metrics for some images from being displayed in the metrics plot.
Full Changelog: https://github.com/Abe404/root_painter/compare/0.2.21...0.2.22
Added functionality to mask images with segmentations (https://github.com/Abe404/root_painter/issues/66). Available from the extras menu.
It is now also possible to have nested datasets (https://github.com/Abe404/root_painter/issues/65).
So now it is possible for users to structure their files like so: datasets/topic_of_interest/specific_dataset
This release includes a bug fix related to loaded image orientation that caused a mismatch between width and height for certain types of JPEG images and their corresponding annotation.
No longer a minimum image size.
Estimated time remaining is shown in segment folder GUI feedback (see inserted image)
The server is now available via pip
pip install root-painter-trainer
start-trainer
Even faster cache for segmentation plot metrics.
Current number of annotated images now shown. Possible to view image in context (see view menu or press Ctrl+C)
Metrics plot available from the extras menu.
Troubleshooting 1: If you can't open the OSX application and receive the error message that the app may be damaged. Running the following from terminal has been found to fix the problem.
xattr -d com.apple.quarantine /Applications/RootPainter.app