Tsuchinoko
Tsuchinoko is a Qt application for adaptive experiment execution and tuning. Live visualizations show details of measurements, and provide feedback on the adaptive engine’s decision-making process. The parameters of the adaptive engine can also be tuned live to explore and optimize the search procedure.
While Tsuchinoko is designed to allow custom adaptive engines to drive experiments, the gpCAM engine is a featured inclusion. This tool is based on a flexible and powerful Gaussian process regression at the core.
A Tsuchinoko system includes 4 distinct components: the GUI client, an adaptive engine, and execution engine, and a core service. These components are separable to allow flexibility with a variety of distributed designs.
Installation
The latest stable Tsuchinoko version is available on PyPI, and is installable with pip
. It is recommended that you
use Python 3.10 for this installation.
pip install tsuchinoko
For more information, see the installation documentation.
Easy Installation
For Mac OSX and Windows, pre-packaged installers are available. These do not require a base Python installation. See the installation documentation for more details.
Getting started with your own adaptive experiments
You can find demos in the Tsuchinoko Github repository’s examples folder.
It is suggested to first try running both server_demo.py
and client_demo.py
simultaneously. This demo performs a
simulated adaptive experiment by making “measurements” sampled from an image file. It is recommended as a first run to follow
the Getting Started guide.
About the name
Japanese folklore describes the Tsuchinoko as a wide and short snake-like creature living in the mountains of western Japan. This creature has a cultural following similar to the Bigfoot of North America. Much like the global optimum of a non-convex function, its elusive nature is infamous.