📝Tips and Tricks in Keras

How to tune the number of epochs and batch_size in Keras-tuner?

Photo by Dave Gandy under the Public Domain Dedication License

Warning: There is no magical formula or Holy Grail here, though a new world might open the door for you.

📈Python for finance series

1. Identifying Outliers
2. Identifying Outliers — Part Two
3. Identifying Outliers — Part Three
4. Stylized Facts
5. Feature Engineering & Feature Selection
6. Data Transformation
7. Fractionally Differentiated Features
8. Data Labelling

This can be done by subclassing the Tuner class you are using and overriding run_trial. (Note that Hyperband sets the epochs to train for via its own logic, so if you're using Hyperband you shouldn't tune the epochs). Here's an example with kt.tuners.BayesianOptimization:

class MyTuner(kerastuner.tuners.BayesianOptimization):
  def run_trial(self, trial, *args, **kwargs):
    # You can add additional HyperParameters for preprocessing and custom training loops
    # via overriding `run_trial`
    kwargs['batch_size'] = trial.hyperparameters.Int('batch_size', 32, 256, step=32)
    kwargs['epochs'] = trial.hyperparameters.Int('epochs', 10, 30)…