Tunny is Grasshopper's optimization component using Optuna, an open source hyperparameter auto-optimization framework.
This component support below optimization algorithms.
- TPE (Bayesian optimization)
- NSGA-II (Genetic algorithm)
- CMA-ES (Evolution strategy)
TPE and NSGA-II also support multi-objective optimization.
It is inspired by components such as Galapagos, opossum, and wallacie, and can be used in a similar way to them.
For more information on how to use it, click here to see document.
The following is taken from the Optuna official website
Optuna™, an open-source automatic hyperparameter optimization framework, automates the trial-and-error process of optimizing the hyperparameters. It automatically finds optimal hyperparameter values based on an optimization target. Optuna is framework agnostic and can be used with most Python frameworks, including Chainer, Scikit-learn, Pytorch, etc.
Optuna is used in PFN projects with good results. One example is the second place award in the Google AI Open Images 2018 – Object Detection Track competition.
Optuna official site : https://optuna.org/
First, Tunny runs on Windows only.
- Download Tunny from this page or release page
- Right-click the .zip file > Properties > make sure there is no "blocked" text
- In Grasshopper, choose File > Special Folders > Components folder. Move Tunny folder you downloaded there.
- Restart Rhino and Grasshopper