PAIR-code / PAIR-code/tiny-transformers
Pass dropout once for whole neural-network
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 24
- Forks
- 6
- PR merge metrics
- No merged PRs in 30d
Description
Currently, we have to set the dropout rate for each layer, and ideally we should only need to set it once.
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
No files or tests are named. Start by locating where layer dropout rates are configured and how the neural network is assembled; done means one network-level dropout setting can be supplied and is applied consistently across the relevant layers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, machine-learning
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100