Opacus Files

Training PyTorch models with differential privacy

This is an exact mirror of the Opacus project, hosted at https://github.com/pytorch/opacus. SourceForge is not affiliated with Opacus. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
Opacus v1.5.2 source code.tar.gz	2024-08-03	1.2 MB	0
Opacus v1.5.2 source code.zip	2024-08-03	1.3 MB	0
README.md	2024-08-03	361 Bytes	0
Totals: 3 Items		2.5 MB	0

New features Add a function of "double_backward" simplifying the training loop (#661)

Bug fixes Fix issue with setting of param_group for the DPOptimizer wrapper (issue 649) (#660) Fix issue of DDP optimizer for FGC. The step function incorrectly called "original_optimizer.original_optimizer" (#662) Replace "opt_einsum.contract" by "torch.einsum"(#663)

Source: README.md, updated 2024-08-03

Other Useful Business Software

Our Free Plans just got better! | Auth0

With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.

Try free now

Cloud tools for web scraping and data extraction

Deploy pre-built tools that crawl websites, extract structured data, and feed your applications. Reliable web data without maintaining scrapers.

Automate web data collection with cloud tools that handle anti-bot measures, browser rendering, and data transformation out of the box. Extract content from any website, push to vector databases for RAG workflows, or pipe directly into your apps via API. Schedule runs, set up webhooks, and connect to your existing stack. Free tier available, then scale as you need to.

Explore 10,000+ tools

Recommended Projects

Appfl
Advanced Privacy-Preserving Federated Learning framework
DiffEqFlux.jl
Pre-built implicit layer architectures with O(1) backprop, GPUs
Lux.jl
Elegant and Performant Deep Learning
7zip Backup Wraper
small backup solution using 7zip
DiffEqBayes.jl
Extension functionality which uses Stan.jl, DynamicHMC.jl

Opacus Files

Training PyTorch models with differential privacy

Get an email when there's a new version of Opacus