google-research / google-research/pix2struct
how can I finetune docvqa on another languange?
Open
- Dominant language
- Python
- Stars
- 690
- Forks
- 61
- PR merge metrics
- No merged PRs in 30d
Description
I wanna use the pretrained docvqa model to continue finetuning.I only change the question to another language,and the labels keep the same,can this solution work out?
Contributor guide
Assessment
This issue has not been assessed yet.