ml-research / ml-research/NeSyConceptLearner
hungarian loss was not decrease when trained slot-attention model
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 21
- Forks
- 3
- PR merge metrics
- No merged PRs in 30d
Description
I like your concept that uses Hungarian matching with slot-attention; I tried to train the model, and I am curious that the loss can not, so is it expected or not?
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
The issue names no files, tests, or entry points. Start by reproducing training for the slot-attention model and inspect the Hungarian loss behavior against the reported setup. Done means determining whether the non-decreasing loss is expected or identifying a reproducible defect.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100