I would suggest using hyperopt (https://github.com/hyperopt/hyperopt) , which uses a kind of Bayesian Optimization for search optimal values of hyperparameters given the objective function. It is more intuitive to use than Spearmint.

PS : There is a wrapper of hyperopt speifically for keras, hyperas (https://github.com/maxpumperla/hyperas). You can also use it.

I would suggest using hyperopt , which uses a kind of Bayesian Optimization for search optimal values of hyperparameters given the objective function. It is more intuitive to use than Spearmint.

PS : There is a wrapper of hyperopt speifically for keras, hyperas. You can also use it.