keras_tuner.Hyperband( hypermodel=None, objective=None, max_epochs=100, factor=3, hyperband_iterations=1, seed=None, hyperparameters=None, tune_new_entries=True, allow_new_entries=True, max_retries_per_trial=0, max_consecutive_failed_trials=3, **kwargs )
Variation of HyperBand algorithm.
Li, Lisha, and Kevin Jamieson. "Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization." Journal of Machine Learning Research 18 (2018): 1-52.
HyperModelclass (or callable that takes hyperparameters and returns a
Modelinstance). It is optional when
Tuner.run_trial()is overriden and does not use
keras_tuner.Objectiveinstance, or a list of
keras_tuner.Objectives and strings. If a string, the direction of the optimization (min or max) will be inferred. If a list of
keras_tuner.Objective, we will minimize the sum of all the objectives to minimize subtracting the sum of all the objectives to maximize. The
objectiveargument is optional when
HyperModel.fit()returns a single float as the objective to minimize.
tf.keras.callbacks.EarlyStopping). Defaults to 100.
max_epochs * (math.log(max_epochs, factor) ** 2)cumulative epochs across all trials. It is recommended to set this to as high a value as is within your resource budget. Defaults to 1.
hyperparametersshould be added to the search space, or not. If not, then the default value for these parameters will be used. Defaults to True.
hyperparameters. Defaults to True.
Trialif the trial crashed or the results are invalid.
Trials. When this number is reached, the search will be stopped. A
Trialis marked as failed when none of the retries succeeded.
Tunersubclasses. Please see the docstring for