ITTONE Création des applications Web

keras – Trying to find the relationship between max_trials and the number of hyperparameters

I am trying to do hyperparameter tuning for a CNN model. I am using a Bayesian Optimizer and searching for optimal hyperparameter values using keras tuner.

Here are some of the hyperparameters i am trying to tune:
1.Batch size
2. Number of layers
3. Filter values in each conv2d layer.
4. Learning rate.

What is the optimal number of ‘max_trial’ value I should give in keras tuner in such case?

Product of the Month September 2016

Source link

Leave a Comment

Your email address will not be published. Required fields are marked *