In this version we refactored much of the code. The goal was to improve readability and to remove unused and redundant code. There is only few changes in functionality, the most relevant one is that the trainer node now also receives the "model size" when downloading a model from the learning loop.
0.9.3
New features: - This version introduces the /about endpoint to provide introspection of what model is currently running on a detector node or if an update is in progress. This is a necessary precondition for https://github.com/zauberzeug/rosys/discussions/33.
0.9.2
fix: - check only ones for corrupted images before running detections
0.9.1
Same as v0.9.0, but v0.9.0 used wrong commit
0.9.0
API changes: - Abstract function progress() is renamed to training_progress()
New Features: - Trainer nodes now also report the progress for downloading data and making predictions
Fixes: - Trainer nodes now exit if training failed instead of running in a endless retry cycle - Trainer nodes now do not send initial IDLE state when continuing a training