Marwan Zouinkhi

 ## Goal : - Enable workflow sharing - Enable accurate reproduction across various image processing and visualization settings. ## Scheme: `fiji://[Plugin][(optional)/subpath]?query` ## Approach :  ### Related : https://github.com/fiji/fiji/pull/333...

+ add to readme [](https://pypi.org/project/dacapo/) [](https://anaconda.org/conda-forge/dacapo) [](

Validation score calculation (e.g. F1 Score) are currently using the model class - Forground/Background weighting Related to issue : https://github.com/janelia-cellmap/dacapo/issues/3 TODO create score using 50/50 Forground/Background weighting or different weighting...

During training, it might be nice to end training before the requested number of iterations has been completed, if training does not seem to be making progress.

seeds ? more logs ?

Maximum raw value after augmentation is between [-1,0] I think the aim was to do [-1,1] but there is a mistake