dmarx / dmarx/Multi-Modal-Comparators
modularity for comparison operators ("reducers")
Open
- Dominant language
- Jupyter Notebook
- Stars
- 39
- Forks
- 4
- PR merge metrics
- No merged PRs in 30d
Description
* currently defaulting to dot product
* add optional normalization for cosine similarity
* add great circle/spherical dists.
* maybe we can use this modularization to set-up preferred losses for intermodal vs intramodal, for example
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.