The Tuner classes in KerasTuner
- Original Link : https://keras.io/api/keras_tuner/tuners/
- Last Checked at : 2024-11-25
The base Tuner class is the class that manages the hyperparameter search process,
including model creation, training, and evaluation. For each trial, a Tuner receives new
hyperparameter values from an Oracle instance. After calling model.fit(...), it
sends the evaluation results back to the Oracle instance and it retrieves the next set
of hyperparameters to try.
There are a few built-in Tuner subclasses available for widely-used tuning
algorithms: RandomSearch, BayesianOptimization and Hyperband.
You can also subclass the Tuner class to customize your tuning process.
In particular, you can override the run_trial function
to customize model building and training.
The base Tuner class
- Tuner class
- get_best_hyperparameters method
- get_best_models method
- get_state method
- load_model method
- on_epoch_begin method
- on_batch_begin method
- on_batch_end method
- on_epoch_end method
- run_trial method
- results_summary method
- save_model method
- search method
- search_space_summary method
- set_state method