Skip to main content

Brownian motion implementations extracted from torchsde

Project description

torchsde_brownian

This library provides the Brownian motion generation code from torchsde version 0.2.5 as a standalone package torchsde_brownian.

It is mainly meant for use in downstream packages such as k-diffusion and diffusers, for where it is a drop-in replacement: the dependency just needs to be changed, and the import for torchsde to torchsde_brownian.

According to the authors of torchsde, that package is currently in maintenance mode, so no further development, aside from possible compatibility fixes, is expected.

All credit for the original implementation goes to the authors of torchsde, Xuechen Li and Patrick Kidger.

The commit history of this repository has been kept intact so as to preserve the provenance of the code and their contributions.

Installation

pip install torchsde_brownian

Requirements: Python >=3.8 and PyTorch >=1.6.0.

Documentation

Available here.

Citation and references

Please find citations and references in torchsde's readme.

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

torchsde_brownian-0.2.5.tar.gz (17.3 kB view hashes)

Uploaded Source

Built Distribution

torchsde_brownian-0.2.5-py3-none-any.whl (21.0 kB view hashes)

Uploaded Python 3

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