How to transfer the multipage pdfs to images(png)?

X-PLUG / mPLUG-DocOwl

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Apache License 2.0

1.17k stars 71 forks source link

How to transfer the multipage pdfs to images(png)? #5

Open Ucas-HaoranWei opened 11 months ago

Ucas-HaoranWei commented 11 months ago

Hi, I am confused that how to transfer the pdf datasets (Deepform、KLC) to multi images with the true key-value GT pairs for each transfered png image? Because the datasets download in DUE-benchmark have no page ID information.

Coobiw commented 10 months ago

Hello，have you ever solved this problem？ I'm also puzzled with this.

HAWLYQ commented 3 months ago

Hi, @Ucas-HaoranWei @Coobiw , for multi-page datasets, we've only used the first page as input so far.