lucidrains / lucidrains/lambda-networks
Image Size
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.5k
- Forks
- 155
- PR merge metrics
- No merged PRs in 30d
Description
Are non-square image blocks allowed for context? Using global context and a non-square dimensions (96, 128), I get an error on this line about dimension size.
`λp = einsum('n m k u, b u v m -> b n k v', rel_pos_emb, v)`
Contributor guide
No contributing guide indexed for this repository
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 by reproducing the error with global context and non-square dimensions (96, 128), focusing on the shown einsum expression. Trace the surrounding implementation to determine whether non-square image blocks are intended to work; done means the behavior is corrected or the unsupported shape is explicitly clarified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100