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/
KerasTuner requires Python 3.8+ and TensorFlow 2.0+.
Install the latest release:
You can also check out other versions in our GitHub repository.
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.
Please refer to the CONTRIBUTING.md for the contributing guide.
Thank all the contributors!
Ask your questions on our GitHub Discussions.
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}}
}
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4