tensorflow / tensorflow/probability

Speed up and tune VQ-VAE hyperparameters for Hugo's binarized MNIST

Open
#134 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

Currently, Hugo's binarized MNIST is slower and doesn't match the performance of MNIST thresholded at 0.5 in the VQ-VAE example. We should understand why this is happening and tune hyperparameters.

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 from the VQ-VAE example and compare Hugo's binarized MNIST with MNIST thresholded at 0.5. Investigate why the binarized version is slower and performs differently, then tune the hyperparameters; done means its speed and performance are understood and brought in line with the comparison case.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, tensorflow
Domain
machine-learning
Issue type
Bug
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.