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
I searched hyper parameters with keras tuner. (executions_per_trial=2)
and I want to know, what hyper parameters sets were tried and how was the score of evaluation metric.
when I used tuner.get_best_hyperparameters(num_trials = 3) it returned 3 parameter sets but it doesn't have information of score of metric.
So I tried print every trials metric record.
I found something strange,
When I checked, the "Best Value So Far"'s MSE was 0.06 but in the record, there ware alot of MSE 0.04~0.05 s.
Why this happen?? what should I trust? Isn't tuner record average of executions_per_trial?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello!
I searched hyper parameters with keras tuner. (executions_per_trial=2)
and I want to know, what hyper parameters sets were tried and how was the score of evaluation metric.
when I used
tuner.get_best_hyperparameters(num_trials = 3)
it returned 3 parameter sets but it doesn't have information of score of metric.So I tried print every trials metric record.
I found something strange,
When I checked, the "Best Value So Far"'s MSE was 0.06 but in the record, there ware alot of MSE 0.04~0.05 s.
Why this happen?? what should I trust? Isn't tuner record average of executions_per_trial?
Have a nice day! thank you
Beta Was this translation helpful? Give feedback.
All reactions