You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
It would be nice to allow the AAD model to be saved after a few replies from the expert.
If the model is saved locally, the expert can continue the analysis some other time by loading the saved model.
This would also enable parallel analysis using multiple definitions of anomaly.
The text was updated successfully, but these errors were encountered:
It is probably not so related to #89, because here we talk about reusing of the initial random forest model to speed-up initial wait time before an expert start to answer to AAD, while in #89 we talk about saving the final expert-trained model.
I think that we can close this issue since zwaad is reimplemented via coniferest (PR #119) and initial model is trained much-much faster now.
It would be nice to allow the AAD model to be saved after a few replies from the expert.
If the model is saved locally, the expert can continue the analysis some other time by loading the saved model.
This would also enable parallel analysis using multiple definitions of anomaly.
The text was updated successfully, but these errors were encountered: