tensorflow / tensorflow/probability

No Layer Benchmarks Available

Open
#473 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

We want to try TFP layers, but there are many, and it's unclear from docs which are better for what scenarios

Instead of each user guessing / experimenting on layer choices (multiple days * many people), would it be possible to make standard benchmarks for the layers against deterministic counterparts from tf.keras.layers?

Just simple standard datasets in vision / nlp / data science would be super handy

This way newbs avoid wasting days grid-searching over different classes of layers

Thanks in advance,
Bionicles

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

No files, tests, entry points, datasets, or benchmark criteria are named. Start by reviewing the TFP layers and their deterministic counterparts in tf.keras.layers, then define standard vision, NLP, and data-science comparisons. Done would mean documented benchmarks that clarify which layer choices suit each scenario.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, keras
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.