We introduce QSTToolkit, a Python library for performing quantum state tomography (QST) on optical quantum state measurement data. The toolkit integrates traditional Maximum Likelihood Estimation (MLE) with deep learning-based techniques to reconstruct quantum states. It includes comprehensive noise models to simulate both intrinsic state noise and measurement imperfections, enabling the realistic recreation of experimental data. QSTToolkit bridges TensorFlow, a leading deep learning framework, with QuTiP, a widely used quantum physics toolbox for Python. This paper describes the library's features, including its data generation capabilities and the various QST methods implemented. QSTToolkit is available at https://pypi.org/project/qsttoolkit/, with full documentation at https://qsttoolkit.readthedocs.io/en/latest/.
@article{arxiv.2503.14422,
title = {QSTToolkit: A Python Library for Deep Learning Powered Quantum State Tomography},
author = {George FitzGerald and Will Yeadon},
journal= {arXiv preprint arXiv:2503.14422},
year = {2025}
}
Comments
13 pages, 8 figures. QSTToolkit is available at https://pypi.org/project/qsttoolkit/. Full documentation at https://qsttoolkit.readthedocs.io/en/latest/