DeepHyper is a powerful Python package for automating machine learning tasks, particularly focused on optimizing hyperparameters, searching for optimal neural architectures, and quantifying uncertainty through the deep ensembles. With DeepHyper, users can easily perform these tasks on a single machine or distributed across multiple machines, making it ideal for use in a variety of environments. Whether you’re a beginner looking to optimize your machine learning models or an experienced data scientist looking to streamline your workflow, DeepHyper has something to offer. So why wait? Start using DeepHyper today and take your machine learning skills to the next level!

DeepHyper is specialized for machine learning tasks but it can also be used for generic black-box and gray-box optimization problems of expensive functions.

The project is organized accross different repositories:

• deephyper: Main Python package providing the Automated Machine Learning tools.
• tutorials: Set of script, notebook or colab tutorials to learn how to use DeepHyper.
• quickstart: Set of installation and basic example scripts to run DeepHyper on specific clusters/systems.
• benchmark: Set of benchmarks to evaluate the performance of DeepHyper.