[Feature request] Pass sensor information to model
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.1k
- Forks
- 264
- Avg merge
- 1d 13m
- Merged PRs (30d)
- 23
Description
I'm making a pretrained model where it uses the sensor's name to calculate some features before passing the recordings into the networks. It would be very useful if the library can support these sensor meta data. Besides pretraining on the same montage as the BCI dataset, this is the only reasonable way to evaluate a pretrained model on downstream BCI tasks without too much hassle.
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 names no files, tests, or entry points. Start by tracing how recordings and sensor metadata are represented before they reach pretrained models, then determine how that metadata should be exposed to downstream BCI models. Done means the library supports passing sensor information through the model input path for the described evaluation use case.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100