PyTorch integration for the OpenDP Library
Project description
OpenDP-PyTorch
OpenDP-PyTorch is an extension to the OpenDP library for differentially private training of pytorch neural networks.
OpenDP-PyTorch is part of the larger OpenDP Project, a community effort to build trustworthy, open source software tools for analysis of private data.
Status
OpenDP-PyTorch is under development, and we expect to release new versions frequently, incorporating feedback and code contributions from the OpenDP Community. This library is not ready to build privacy-sensitive applications.
OpenDP, like all real-world software, has both known and unknown issues. If you intend to use OpenDP for a privacy-critical application, you should evaluate the impact of these issues on your use case.
More details can be found in the Limitations section of the User Guide.
Installation
The easiest way to install OpenDP-PyTorch is using pip
(the package installer for Python):
$ pip install opendp-pytorch
More information can be found in the Getting Started section of the User Guide.
Documentation
Documentation is not yet available for the PyTorch extension.
Getting Help
If you're having problems using OpenDP, or want to submit feedback, please reach out! Here are some ways to contact us:
- Ask questions on our discussions forum
- Open issues on our issue tracker
- Send general queries to info@opendp.org
- Reach us on Twitter at @opendp_org
Contributing
OpenDP is a community effort, and we welcome your contributions to its development! If you'd like to participate, please see the Contributing section of the Developer Guide
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
File details
Details for the file opendp_pytorch-0.1.0-py3-none-any.whl
.
File metadata
- Download URL: opendp_pytorch-0.1.0-py3-none-any.whl
- Upload date:
- Size: 21.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.25.1 setuptools/41.4.0 requests-toolbelt/0.9.1 tqdm/4.49.0 CPython/3.8.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | e23a4ab3d5ab0ab459ee2e95d4447fca38a92ebcca32f6c47d00ee02eb37fbe6 |
|
MD5 | 4034dfb3efdc95ec10ab7b063a326967 |
|
BLAKE2b-256 | 1f1dd1d70bb9fb91bc13d1e116a031fa8adc417ff6eb86d1c87d696bbb549974 |