tensorflow / tensorflow/probability

Variational inference for Conv2D layers

Open
#1,813 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

Hello,
I have been trying to use variational inference to the MLP and CNN (conv2D) layers for my research.
Unlike a comprehensive discussion and examples for probabilistic MLP layers, I could not find any resources implying whether tensorflow_probability has also released VI for the conv2D layers.
My network is built of a combination of MLP-CNN layers and I need to define probabilistic layers for all types of layers in my code. I would appreciate it if you could guide me through finding VI for CNN.

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

The issue names no files, tests, or entry points. Start by reviewing the existing probabilistic MLP resources and checking TensorFlow Probability's Conv2D support; done would be a documented answer or a clearly scoped implementation path for variational inference in CNN layers.

Written by the indexing model from the issue text.

Assessment

Tech stack
tensorflow
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.