DocVQA reproduce problem using StructuralLM
Open
- Dominant language
- Python
- Stars
- 2k
- Forks
- 301
- PR merge metrics
- No merged PRs in 30d
Description
I tried to finetune StructuralLM on DocVQA dataset using the released weights, but I only get 76.85 ANLS on the test set.
Can the finetuning code on DocVQA be open-sourced ?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the released StructuralLM weights and the DocVQA reproduction setup described in the issue, then compare the reported 76.85 ANLS result with the expected evaluation. Done means making the DocVQA finetuning code available and documenting how to run it and verify the result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100