tensorflow / tensorflow/probability

Training for the parameters of a probabilistic model does not work when use .trainable_variables

Open
#1,431 1 comment 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

Look at the following code example, y_dist.trainable_variables is empty. But if declare the training parameter as a list (beta parameter here) it works.

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 by reconstructing the reported example and inspect y_dist.trainable_variables alongside the separately declared beta parameter. Confirm the differing behavior and identify the relevant TensorFlow Probability model entry point; done means the model exposes the expected trainable parameter through trainable_variables.

Written by the indexing model from the issue text.

Assessment

Tech stack
tensorflow
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.