tensorflow / tensorflow/probability

No documentation for kernel_prior and kernel_posterior

Open
#778 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

layers
Dominant language
Jupyter Notebook
Stars
4.4k
Forks
1.1k
PR merge metrics
No merged PRs in 30d

Description

The Bayesian layers have the properties kernel_prior and kernel_posterior, but this is not documented on the right menu of the documentation page of the corresponding class. Clearly, one may need to access these properties (e.g. for plotting, as it is done in the Bayesian NN example). Although I haven't checked it, the documentation for the other related properties (biases, etc.) is probably also missing.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the linked DenseFlipout API documentation and the referenced dense_variational.py properties. Check which kernel and bias properties are absent from the class documentation, then update the relevant API documentation so these properties are listed and usable for the Bayesian neural network example.

Written by the indexing model from the issue text.

Assessment

Domain
documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.