Tomosipo
High-performance 3D tomography with flexible geometries in Python
Tomosipo is a pythonic wrapper for the ASTRA-toolbox of high-performance GPU primitives for 3D tomography.
The aim of tomosipo is to:
Expose a user-friendly API for 3D tomography;
Enable easy manipulation and visualisation of 3D geometries;
Express high-performance GPU-accelerated algorithms succinctly.
First steps
Are you new to tomosipo? This is the place to start!
From scratch: Installation
Tutorials: Creating a tomographic projection | A simple SIRT reconstruction
Advanced Tutorials: Fast SIRT reconstruction using PyTorch on the GPU | Lab frame: rotating object instead of rotating detector
How the documentation is organized
Tomosipo has different types of documentation. A high-level overview of how it’s organized will help you know where to look for certain things:
Tutorials take you by the hand through a series of steps to create a tomographic reconstruction. Start here if you’re new to tomosipo or tomography.
Topic guides discuss key topics and concepts at a fairly high level and provide useful background information and explanation.
Reference guides serve as technical reference for APIs and other aspects of tomosipo’s machinery.
How-to guides are recipes. They guide you through the steps involved in addressing key problems and use-cases. They are more goal-oriented than tutorials and assume some knowledge of how tomosipo works.