How does keras tuner count objective? #581
Unanswered
GustawOhler
asked this question in
Q&A
Replies: 1 comment
-
|
The best score of a trial is the mean of the best epoch of all executions. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
When I tuned my model with Bayesian tuner it seemed to me that it takes the best value across all executions. It didn't fit my needs so I changed to Random tuner and now it seems that it takes some sort of average but I don't know if it's from best scores from all executions or all epochs of all executions. So - like in title - how does the keras tuner count objective for comparing trials?
Beta Was this translation helpful? Give feedback.
All reactions