SPyRiT

SPyRiT is a PyTorch-based image reconstruction package designed for single-pixel imaging. SPyRiT has a modular organisation and may be useful for other inverse problems.

Github repository: openspyrit/spyrit

Installation

SPyRiT is available for Linux, MacOs and Windows:

pip install spyrit

See here for advanced installation guidelines.

Getting started

Please check our tutorials as well as the examples on GitHub.

Cite us

When using SPyRiT in scientific publications, please cite [v3] for SPyRiT v3, [v2] for SPyRiT v2, and [v1] for DC-Net.

[v3]

JFJP Abascal, T Baudier, R Phan, A Repetti, N Ducros, “SPyRiT 3.0: an open source package for single-pixel imaging based on deep learning,” Preprint (2024).

[v2]

G Beneti-Martin, L Mahieu-Williame, T Baudier, N Ducros, “OpenSpyrit: an Ecosystem for Reproducible Single-Pixel Hyperspectral Imaging,” Optics Express, Vol. 31, Issue 10, (2023). DOI.

[v1]

A Lorente Mur, P Leclerc, F Peyrin, and N Ducros, “Single-pixel image reconstruction from experimental data using neural networks,” Opt. Express, Vol. 29, Issue 11, 17097-17110 (2021). DOI.

Join the project

The list of contributors can be found here. Feel free to contact us by e-mail for any question. Direct contributions via pull requests (PRs) are welcome.

Contents

`spyrit.core`	Core module for Spyrit package, containing the main classes and functions.
`spyrit.misc`	Contains miscellaneous Numpy / Pytorch functions useful for spyrit.core.
`spyrit.external`	This module uses a modified version of the Unet presented in https://github.com/cszn/DPIR/blob/master/models/network_unet.py