KerasTuner

KerasTuner is an easy-to-use, scalable hyperparameter optimization framework that solves the pain points of hyperparameter search. Easily configure your search space with a define-by-run syntax, then leverage one of the available search algorithms to find the best hyperparameter values for your models. KerasTuner comes with Bayesian Optimization, Hyperband, and Random Search algorithms built-in, and is also designed to be easy for researchers to extend in order to experiment with new search algorithms.

Official Website: https://keras.io/keras_tuner/

Quick links

• Getting started with KerasTuner
• KerasTuner developer guides
• KerasTuner API reference

Installation

KerasTuner requires Python 3.7+ and TensorFlow 2.0+.

Install the latest release:

pip install keras-tuner --upgrade

You can also check out other versions in our GitHub repository.

Quick introduction

Import KerasTuner and TensorFlow:

import keras_tuner
from tensorflow import keras

Write a function that creates and returns a Keras model. Use the hp argument to define the hyperparameters during model creation.

def build_model(hp):
  model = keras.Sequential()
  model.add(keras.layers.Dense(
      hp.Choice('units', [8, 16, 32]),
      activation='relu'))
  model.add(keras.layers.Dense(1, activation='relu'))
  model.compile(loss='mse')
  return model

Initialize a tuner (here, RandomSearch). We use objective to specify the objective to select the best models, and we use max_trials to specify the number of different models to try.

tuner = keras_tuner.RandomSearch(
    build_model,
    objective='val_loss',
    max_trials=5)

Start the search and get the best model:

tuner.search(x_train, y_train, epochs=5, validation_data=(x_val, y_val))
best_model = tuner.get_best_models()[0]

To learn more about KerasTuner, check out this starter guide.

Contributing Guide

Please refer to the CONTRIBUTING.md for the contributing guide.

Thank all the contributors!

Community

Please use the Keras Slack workspace, the #keras-tuner channel for communication.

Use this link to request an invitation to the channel.

Citing KerasTuner

If KerasTuner helps your research, we appreciate your citations. Here is the BibTeX entry:

@misc{omalley2019kerastuner,
	title        = {KerasTuner},
	author       = {O'Malley, Tom and Bursztein, Elie and Long, James and Chollet, Fran\c{c}ois and Jin, Haifeng and Invernizzi, Luca and others},
	year         = 2019,
	howpublished = {\url{https://github.com/keras-team/keras-tuner}}
}