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