cmrsim 0.31

No project description provided

Welcome to CMRsim!

CMRsim is a MRI - simulation framework that features bloch-simulations as well as analytic signal evaluations for moving objects with an easy to use API written in pure python. The computationally demanding calculations are implemented in TensorFlow2 and therefore are seamlessly executable on CPU and GPU environments, while also making efficient use of computational resources!

What makes CMRsim special?

• CMRsim features bloch-simulations as well as simulations using analytical signal equations and even allows to combine elements of both.

• Convenient support for moving particles!

• Modularity that makes to designing comparative simulation experiments convenient.

• Architecture and implementation that allows to easily include your own simulation modules.

• Reproducibility by using versioned and documented open-source software.

• Easily scalable to detailed digital phantoms

Installation

Pip

CMRsim can be installed using the python package manager pip. The package can be found in the registry of the repository hosted on the ETH-Gitlab instance as well as on the python package index (PyPI).

Versioning: Stable release versions are denoted with the ususal major.minor notation. Additionally, development versions are constantly updated on solved issued and can be installed using the major.minor.devX notation

Release versions are published on PyPI, which allows installing cmrsim with:

pip install cmrsim

Development versions are only available using the extra url:

pip install cmrsim --extra-index-url https://gitlab.ethz.ch/api/v4/projects/23798/packages/pypi/simple

To install cuda and cdnn for GPU accellaration (requires nvidia drivers to be installed on your system), from version 0.31 you can use:

pip install cmrsim[cuda]

Docker

For each major release a set of docker images are compiled and published in the container registry associated with repository. Within the docker images, all requirements are installed for simulation deployment.

Furthermore, there are three image-tags available. To use the pull the docker image use (e.g. for jupyter tag):

docker pull registry.ethz.ch/jweine/cmrsim/jupyter:latest

CPU

Based on the Tensorflow:…-cpu:latest docker image. Containing all cmrsim dependencies and cmrsim

GPU

Based on the Tensorflow:…-gpu:latest docker image. Containing all cmrsim dependencies and cmrsim

Jupyter

Based on the gpu:latest tag, but also includes an installation of jupyter-lab for interactive simulation / rendering.