Skip to main content

pygmtools provides graph matching solvers in Python API and supports numpy and pytorch backends. pygmtools also provides dataset API for standard graph matching benchmarks.

Project description


PyPi version PyPI pyversions Documentation Status GitHub stars

pygmtools provides graph matching solvers in Python and is easily accessible via the following command:

pip install pygmtools


By default the solvers are executed on the numpy backend, and the required packages will be automatically downloaded.

For advanced and professional users, the pytorch backend is also available if you have installed and configured a pytorch runtime. The pytorch backend exploits the underlying GPU-acceleration feature, and also supports integrating graph matching modules into your deep learning pipeline.


To highlight, pygmtools has the following features:

  • Support various backends, including numpy which is universally accessible, and the state-of-the-art deep learning architecture pytorch with GPU-support. The support of the following backends are also planned: tensorflow, mindspore, paddle, jittor;
  • Support various solvers, including traditional combinatorial solvers and novel deep learning-based solvers;
  • Deep learning friendly, the operations are designed to best preserve the gradient during computation and batched operations support for the best performance.


pygmtools is also featured with standard data interface of several graph matching benchmarks. We also maintain a repository containing non-trivial implementation of deep graph matching models, please check out ThinkMatch if you are interested!

Developers and Maintainers

pygmtools is currently developed and maintained by members from ThinkLab at Shanghai Jiao Tong University.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pygmtools-0.2.2.tar.gz (44.1 kB view hashes)

Uploaded source

Built Distribution

pygmtools-0.2.2-py3-none-any.whl (46.2 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page