Quickstart | Install guide | API Docs
Simbi allows ultracold atom clouds to be simulated after time-of-flight expansion. This includes thermal clouds, Bose-Einstein condensates or a mixture of the two. This package was created to generate simulated datasets of ultracold atom cloud images. These simulated datasets can then be used to train deep neural networks.
Currently the package only relies on Numpy and Scipy, although in the future the functions will be calculated with JAX which will allow for GPU speedups.
The easiest way to test out SimBi is using a Colab notebook. We have a few tutorial notebooks including:
SimBi is written in Python and can be installed via pip
pip install simbi
For details about the SimBi API, see the reference documentation.