Repository files navigation

Documentation

This is a PyTorch implementation ofDeep Graph Matching Consensus, as described in our paper:

Matthias Fey, Jan E. Lenssen, Christopher Morris, Jonathan Masci, Nils M. Kriege:Deep Graph Matching Consensus(ICLR 2020)

• PyTorch (>=1.2.0)
• PyTorch Geometric (>=1.5.0)
• KeOps (>=1.1.0)

$ python setup.py install

Head over to ourdocumentation for a detailed overview of theDGMC module.

We provide training and evaluation procedures for thePascalVOC with Berkely annotations dataset, theWILLOW-ObjectClass dataset, thePascalPF dataset, and theDBP15K dataset.Experiments can be run via:

$ cd examples/$ python pascal.py$ python willow.py$ python pascal_pf.py$ python dbp15k.py --category=zh_en

Please citeour paper if you use this code in your own work:

@inproceedings{Fey/etal/2020,  title={Deep Graph Matching Consensus},  author={Fey, M. and Lenssen, J. E. and Morris, C. and Masci, J. and Kriege, N. M.},  booktitle={International Conference on Learning Representations (ICLR)},  year={2020},}

$ python setup.py test