tensorflow / tensorflow/probability
Training for the parameters of a probabilistic model does not work when use .trainable_variables
Open
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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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