salesforce / salesforce/LayoutDETR
not supports multimodal(text+image) input!
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 107
- Forks
- 16
- PR merge metrics
- No merged PRs in 30d
Description
The current code only supports text input and does not support text+images input. Can you provide the code for this part?
(当前的代码只支持输入文本，不支持文本+图片，我没有找到支持文本+图片作为输入的代码！)
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 does not identify files, tests, or an entry point. Begin by tracing the current text-input path through the repository and locating the model and data-loading components described by the issue. Define the required text-plus-image input behavior and validation before implementing it; done means the repository accepts and processes both modalities with a verifiable example or test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100