Skip to main content

A framework for topological machine learning based on `pytorch`.

Project description

`pytorch-topological` icon

pytorch-topological: A topological machine learning framework for pytorch

pytorch-topological (or torch_topological) is a topological machine learning framework for PyTorch. It aims to collect loss terms and neural network layers in order to simplify building the next generation of topology-based machine learning tools.

torch_topological is still a work in progress. Stay tuned for more information.

Installation

It is recommended to use the excellent poetry framework to install torch_topological:

poetry add torch-topological

Alternatively, use pip to install the package:

pip install -U torch-topological

Dependencies

torch_topological is making heavy use of giotto-ph, a high-performance implementation of Ripser.

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

torch_topological-0.1.0.tar.gz (7.1 kB view details)

Uploaded Source

Built Distribution

torch_topological-0.1.0-py3-none-any.whl (9.2 kB view details)

Uploaded Python 3

File details

Details for the file torch_topological-0.1.0.tar.gz.

File metadata

  • Download URL: torch_topological-0.1.0.tar.gz
  • Upload date:
  • Size: 7.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.1.11 CPython/3.9.9 Linux/5.15.7-arch1-1

File hashes

Hashes for torch_topological-0.1.0.tar.gz
Algorithm Hash digest
SHA256 4d52dbced924f3619814b06bde558eea9243f2403e7ab62c375bf08a92342e28
MD5 dabf6cb8d35faff44a063513bbe74f74
BLAKE2b-256 e429ed81331a7500669d1666370f7ba0c7eac1ac617948c0c2b02743d7723ef5

See more details on using hashes here.

File details

Details for the file torch_topological-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: torch_topological-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 9.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.1.11 CPython/3.9.9 Linux/5.15.7-arch1-1

File hashes

Hashes for torch_topological-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e797b6aa0364b0839fbb2bf0432371bbb30fafeb3aa3069ded581d84fa92454e
MD5 1913cb63b4d5e9f77ab2fcc01221ed0f
BLAKE2b-256 2798d444fd33996ff84f3c5990cfc1c83fbfdb954aebf01fd1c88346298d07bf

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page