Could you share the finetuned weights for image-text retrieval?
- Dominant language
- Python
- Stars
- 799
- Forks
- 111
- PR merge metrics
- No merged PRs in 30d
Description
Hi all.
I'm Henry Lee, a graduate student at Seoul National University.
Thanks for sharing your great work for future research.
If you don't mind, could you share the fine-tuned weights of COCO image-text retrieval?
As you mentioned in the repo, it's really heavy so I could not fine-tune with the GPUs I can use in our university.
I do not need the exact same parameters that are reported in the paper, I just want to use them for other tasks.
Thank you in advance.
Henry
Contributor guide
No contributing guide indexed for this repository
Research direction
No file, test, or entry point is named. Start by reviewing the repository's guidance for COCO image-text retrieval and the referenced paper details, then determine whether the requested fine-tuned weights exist or can be produced with the available training setup. Done means the weights are available for the requested downstream use.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100