Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add modified Bayesian regression tutorial with more direct PyTorch usage #2996

Open
wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

Add modified Bayesian regression tutorial with more direct PyTorch usage #2996

wants to merge 1 commit into from

Commits on Dec 10, 2021

  1. Add new option for PyroModule parameters to be stored locally, rather… 

    … than the global parameter store. Add backwards-compatible __call__ method to pyro.infer.ELBO that returns a Module bound to a specific model and guide, allowing direct use of the PyTorch JIT API. Fork Bayesian regression tutorial into a PyTorch API usage tutorial to illustrate a PyTorch-native programming style facilitated by these changes and PyroModule.
    @eb8680
    eb8680 committed Dec 10, 2021
    Configuration menu
    Copy the full SHA
    e3af797 View commit details
    Browse the repository at this point in the history