Sovereign 8s.is mirror of standardgalactic/cac
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
2026-02-09 19:01:38 +01:00
examples Add files via upload 2026-02-06 14:06:25 +01:00
no_gpu Update 2025-07-16 15:17:14 +02:00
src/cac Update train.py 2026-02-06 13:48:23 +01:00
with_gpu Update 2025-07-16 15:18:06 +02:00
INSTALLATION.txt Installation file 2024-10-03 14:42:42 +02:00
LICENSE Initial commit 2024-10-03 14:07:25 +02:00
README.md Update README.md 2026-02-09 19:01:38 +01:00
setup.py Update setup.py 2025-07-16 15:36:03 +02:00

Chip Analyzer and Calculator (cac)

An open-source Python library for applying data-driven and process-based machine learning methods to analyze microfluidics experiments

Introduction

cac provides data-driven and process-based machine learning methods for enabling efficient and real-time analysis of microfluidics experiments. It uses Keras and Tensorflow for the implementation of data-driven machine learning methods, and OpenCV for image processing. It enables training with GPU, built on Horovod.

The process-based machine learning implementation uses Keras and Tensorflow library. It automatically applied optimization using Bayesian Optimization with Hyperband (BOHB) algorithm from bohb-hpo repository. Users can use the process-based machine learning method with minimum changes.

Simulator for microfluidics experiments

To provide training samples for constructing machine learning models, we frequently use Lattice-Boltzmann method. The Lattice-Boltzmann code can be downloaded through this link: lbm and should be used in conjuction with cac.

Getting started

Please check INSTALLATION.txt for detailed steps for installing the library.

Contact us

For further questions or inquiries, please contact Ryan Santoso - r.santoso@fz-juelich.de