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

Installation

KerasTuner requires Python 3.8+ and TensorFlow 2.0+.

Install the latest release:

pip install keras-tuner

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

Ask your questions on our GitHub Discussions.

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}}
}

Release files for keras-tuner 1.4.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for keras-tuner 1.4.4
File	Size	Uploaded
keras-tuner-1.4.4.tar.gz	79.0 kB	Oct 2, 2023	Details

Built distribution (wheel)

Table of built distributions (wheels) for keras-tuner 1.4.4
File	Interpreter	ABI	Platform	Reset
keras_tuner-1.4.4-py3-none-any.whl 128.0 kB Oct 2, 2023	Python 3	none	any	Details

Total release size: 207.0 kB

Release files / keras-tuner-1.4.4.tar.gz

Download URL	keras-tuner-1.4.4.tar.gz
Size	79.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`f2b53bed90a24c4f0e761d9bf5acc1a71b879f7b043f5aad5c3c054586ee828c`
BLAKE2b-256 checksum How to use checksums	`5c4ca561ceab08eee85a79d43327ee64bfb13e251e9b8532bb10d229728dce58`
Upload date	Oct 2, 2023
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.11.5`

Release files / keras_tuner-1.4.4-py3-none-any.whl

Download URL	keras_tuner-1.4.4-py3-none-any.whl
Size	128.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`d38c07ee50ec6fb321baa0dabc6f73a10c3a9d9f5b5b8d7c002d6e52b98b2f2e`
BLAKE2b-256 checksum How to use checksums	`b3fb35dab32ffc45faefcb6762088a1c105e421fbd253eb3e86002b70916e6f3`
Upload date	Oct 2, 2023
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.11.5`