A PyTorch library for differentiable submodular minimization.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
docs
notebooks
src
tests
torch_submod
.gitignore
.travis.yml
license.txt
readme.md
setup.cfg
setup.py

readme.md

torch-submod

Documentation Status Build Status

A PyTorch library for differentiable submodular minimization.

At the moment only one- and two-dimensional graph cut functions have been implemented, so that this package provides differentiable (with respect to the input signal and the weights) total variation solvers.

Please refer to the documentation for more information about the project. You can also have a look at the following notebook that showcases how to learn weights for image denoising.

Installation

After installing PyTorch, you can install the package with:

python setup.py install

Testing

To run the tests you simply have to run:

python setup.py test

Bibliography

  • [DK17] J. Djolonga and A. Krause. Differentiable learning of submodular models. In Advances in Neural Information Processing Systems (NIPS), 2017.
  • [NB17] V. Niculae and M. Blondel. A regularized framework for sparse and structured neural attention. arXiv preprint arXiv:1705.07704, 2017.