HazyResearch/pdftotree

How to reproduce the vision model?

HiromuHota opened this issue · 1 comments

Describe the bug

A vision-based model has been introduced at #29.
Are there a script and a dataset to reproduce this model?

To Reproduce

No way to reproduce the model.

Expected behavior

A pointer to a script and a dataset that can reproduce the model.

Error Logs/Screenshots

N/A

Environment (please complete the following information):

N/A

Additional context
Add any other context about the problem here.

@ines-chami Do you perhaps remember any details about reproducing the vision-based model?