Skip to content

Latest commit

 

History

History
72 lines (37 loc) · 3.93 KB

README.md

File metadata and controls

72 lines (37 loc) · 3.93 KB
Raw

PyLissom Build Status Documentation Status Maintainability Scrutinizer Code Quality codecov

The LISSOM family of self-organizing computational models aims to replicate the detailed development of the visual cortex of humans.

PyLissom is a Pytorch extension implementing the LISSOM networks. It's split in two parts: the core nn and optim packages, which implement the LISSOM network itself, and the datasets, models, and utils packages.

Some of the datasets, models and utils of PyLissom were inspired by Topographica, a former implementation of the LISSOM networks oriented in its design to the neuroscience community. Instead, PyLissom was designed for a hybrid use case of the machine learning and the neuroscience communities.

Getting Started

The library and API documentation are at: https://pylissom.readthedocs.io/, you should check it out for a high level overview. There is an UML class diagram for reference. For hands-on examples there are jupyter notebooks at notebooks/. If Github is not rendering them, we leave these links at your disposal:

Lissom modules

Linear modules

Optimizers

Orientation Maps and pylissom tools

The main features provided by pylissom are:

  • LISSOM's activation

  • LISSOM's hebbian learning mechanism and others

  • Configuration and model building tools

  • Common Guassian stimuli for LISSOM experiments

  • Plotting helpers

  • Training pipeline objects

Installation

You should first install PyTorch with conda as explained at: https://pytorch.org/

Then you can install PyLissom by running:

pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple pylissom

The code is hosted in pypi: https://test.pypi.org/project/pylissom/

Contributing

The tests are in the tests/ folder, and can be run with pytest. Also, the repository has Travis CI enabled, meaning every commit and Pull Request runs the tests in a virtualenv, showing as green checkmarks and red crosses in the PR page. These are all the integrations links of the repo:

Travis - Continuous Integration: repo_page

Codecov - Code coverage: repo_page

Scrutinizer - Code health: repo_page

CodeClimate - Maintainability: repo_page

ReadTheDocs - Documentation: repo_page

For any questions please contact the repo collaborators.

License

The project is licensed under the GPLv3 license.