Skip to content
Deep Declarative Networks
Jupyter Notebook Python
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
apps
ddn added simplex gradient Oct 15, 2019
tests added restarts to robust pooling; ensure correct dimensions for compo… Sep 26, 2019
tutorials added some clarification Oct 11, 2019
.gitignore
LICENSE
README.md
setup.py Update setup.py Sep 7, 2019

README.md

Deep Declarative Networks

Deep Declarative Networks (DDNs) are a class of deep learning model that allows optimization problems to be embedded within an end-to-end learnable network. This repository maintains code and resources for developing and understanding DDN models.

You can find more details in this paper, which if you would like to reference in your research please cite as:

@techreport{Gould:PrePrint2019,
  author      = {Stephen Gould and
                 Richard Hartley and
                 Dylan Campbell},
  title       = {Deep Declarative Networks: A New Hope},
  eprint      = {arXiv:1909.04866},
  institution = {Australian National University (arXiv:1909.04866)},
  month       = {Sep},
  year        = {2019}
}

Running code

When running code from the command line make sure you add the ddn package to your PYTHONPATH. For example:

export PYTHONPATH=${PYTHONPATH}:ddn
python tests/testBasicDeclNodes.py

Tutorials should be opened in Jupyter notebook:

cd tutorials
jupyter notebook

Reference (PyTorch) applications for image and point cloud classification can be found under the apps directory. See the README files therein for instructions on installation and how to run.

License

The ddn library is distributed under the MIT license. See the LICENSE file for details.

You can’t perform that action at this time.