keras-team/keras-tuner

Health v2 · maintenance only

Adoption not part of the score

2923 stars · 404 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

KerasTuner is a hyperparameter optimization framework for Keras models with a define-by-run syntax for configuring search spaces. It ships with Random Search, Bayesian Optimization, Hyperband, and Grid Search algorithms and is extensible for custom search strategies.

Use cases

• tune hyperparameters of a keras neural network
• find the best number of units and learning rate for my model
• run hyperparameter search with bayesian optimization
• use hyperband to prune bad trials early
• define a search space inline while building the model
• extend a custom search algorithm for hyperparameter tuning
• tune sklearn models

When to choose

• you train Keras or TensorFlow models and want automated hyperparameter search
• you want define-by-run search space configuration in Python
• you need built-in Bayesian Optimization, Hyperband, or Random Search
• you are a researcher prototyping new tuning algorithms

When to avoid

• you use PyTorch or JAX without Keras
• you need general AutoML beyond hyperparameter tuning (e.g., architecture search pipelines)
• you want a framework-agnostic tuner like Optuna

Facets

library · maturity active

machine-learning deep-learning benchmarking machine-learning deep-learning artificial-intelligence python cross-platform hyperparameter-optimization automl keras tensorflow bayesian-optimization hyperband random-search

Member repositories

For agents

markdown · JSON · MCP: product_card(name="keras-team/keras-tuner")