I have an existing hyperparameter search in Keras using kerastuner.tuners.RandomSearch
. It looks like this:
tuner = RandomSearch(build_model,
objective='val_loss',
max_trials=18,
executions_per_trial=3,
)
I look at dask documentation and I don't see any equivalent call, particularly for specifying the objective as 'val_loss'. Is there an equivalent in dask to the above statement? My goal is to (see if) speed up the tuner search process.