This is the code written in conjunction with the first part of the author's Master's thesis on GUM-compliant neural network robustness verification. The code was written for Python 3.10.
The final submission date was 23. January 2023.
The INSTALL guide assists in installing the required packages. After that take a look at our example script.
The documentation can be found on ReadTheDocs.
This software is developed under the sole responsibility of Björn Ludwig (the author in the following). The software is made available "as is" free of cost. The author assumes no responsibility whatsoever for its use by other parties, and makes no guarantees, expressed or implied, about its quality, reliability, safety, suitability or any other characteristic. In no event will the author be liable for any direct, indirect or consequential damage arising in connection with the use of this software.
pytorch_gum_uncertainty_propagation is distributed under the MIT license.