docs: add disclaimer that winnow is not an approved Frigate training method
This commit is contained in:
@@ -2,6 +2,8 @@
|
||||
|
||||
[](https://github.com/sudolulo/winnow/actions/workflows/docker-publish.yml) [](https://github.com/sudolulo/winnow/actions/workflows/test.yml) [](https://github.com/sudolulo/winnow/releases/latest) [](LICENSE) [](https://immich.app) [](https://frigate.video)
|
||||
|
||||
> **Note:** winnow's approach to training Frigate face recognition is not an officially documented workflow — results may vary.
|
||||
|
||||
> **Early Development — Use With Caution**
|
||||
> winnow is functional but still maturing. Features that modify your Frigate training data — quality replacement, stale mapping cleanup — can remove images from your dataset and are not yet battle-tested at scale. Review the logs after each run and keep backups of your Frigate face training directory until you are confident in the results.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user