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 add an example of using optuna with skorch. The main reason is that GridSearchCV and RandomizedSearchCV can be much too slow for certain neural networks. Optuna has the potential to be much faster.
This example could be a starting point. As to how, possibilities are a Python script, a Jupyter notebook, or an extension of the docs. Maybe even some of those, like adding a code example and a new chapter in the docs about hyper parameter search.
The text was updated successfully, but these errors were encountered:
It would be nice to add an example of using optuna with skorch. The main reason is that
GridSearchCV
andRandomizedSearchCV
can be much too slow for certain neural networks. Optuna has the potential to be much faster.This example could be a starting point. As to how, possibilities are a Python script, a Jupyter notebook, or an extension of the docs. Maybe even some of those, like adding a code example and a new chapter in the docs about hyper parameter search.
The text was updated successfully, but these errors were encountered: