tensorflow / tensorflow/probability

Please update the reference tfp.bijector.BatchNormalization

Open
#587 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement tensorflow 2.0
Dominant language
Jupyter Notebook
Stars
4.4k
Forks
1.1k
PR merge metrics
No merged PRs in 30d

Description

Here is the colab about the Problem.

https://colab.research.google.com/gist/MokkeMeguru/055440bb1eefbe58badbfe81eab73409/batchnormalization_test.ipynb

  • The main problem is your reference uses some old functions. Please update them.

  • Another problem is event_shape for BatchNormalization.
    BatchNormalization is affected over the batch axis.
    But event_shape in tfdTransformedDistribution usually demands the shapes without the batch axis.
    I'm wondering if this transformation works correctly.

Thanks!

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 Colab reproducer and inspect its BatchNormalization examples, including the use of event_shape in tfd.TransformedDistribution. Compare the referenced functions with current APIs and determine whether the transformation handles the batch axis correctly; done means the outdated references are updated and the event-shape behavior is verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.