Keras functionnal models for parametric UMAP ?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.3k
- Forks
- 871
- Avg merge
- 1d 13h
- Merged PRs (30d)
- 5
Description
I want to use one of my keras model for parametric UMAP. However my model is rather complex (with multiple heads) to deal with multiple data format. So it doesn't really fit in a sequential model. Would there be any way to use the non-seuqential model in parametric UMAP ?
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
The issue asks whether parametric UMAP can use a non-sequential Keras model with multiple heads. No files or tests are named, so start by locating the parametric UMAP model interface and reviewing its Keras assumptions. Done would require a decided, documented approach for supporting the reported multi-format model, with tests if support is added.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- keras, python, tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100