Welcome to CalCIL’s documentation!

CalCIL is a computational imaging library that provides gradient descent-based image reconstruction tools. It is designed to be modular and extensible, with a focus on ease of use and reproducibility. CalCIL is built on top of JAX and Flax.

Features

• 🧠 brainless gradient descent-based image reconstruction

• 🤓 fully customizable loss functions

• 🫡 auto logging and visualization via tensorboard

• 😬 flexible optimization parameters (variable specific settings, learning rate schedule, etc.)

• 🤯 post-update custom functions

• 🔮 handy helper functions for interactive 3/4D visualization on jupyter notebook

Contents:

• Installation
  • Prerequisites
  • Step-by-step Installation
• Getting started
  • Defining a convolution forward model
  • Using the forward model to simulate an imaging system
  • Running deconvolution with gradient descent
• History of this project
• CalCIL
  • calcil package

Indices and tables

• Index

• Module Index

• Search Page