keras-team/keras-tuner
A Hyperparameter Tuning Library for Keras
When building machine learning models with Keras, this project helps you automatically find the optimal settings for your model's 'hyperparameters' (like how many layers it has or the learning rate). You provide your Keras model definition with some flexibility, and it outputs the best-performing model based on your criteria. This is for machine learning engineers, data scientists, and researchers who develop and fine-tune deep learning models.
2,917 stars. Used by 9 other packages. Available on PyPI.
Use this if you are developing Keras deep learning models and want to efficiently discover the best model architecture and training parameters without extensive manual trial and error.
Not ideal if you are not using Keras or if your models do not involve deep learning, as it is specifically designed for Keras models and their complex hyperparameters.
Stars
2,917
Forks
404
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 01, 2025
Commits (30d)
0
Dependencies
6
Reverse dependents
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/keras-team/keras-tuner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
optuna/optuna
A hyperparameter optimization framework
KernelTuner/kernel_tuner
Kernel Tuner
syne-tune/syne-tune
Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
deephyper/deephyper
DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning
optuna/optunahub
Python library to use and implement packages in OptunaHub