search

shabie / docformer

Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU)
MIT License
253 stars 40 forks source link

How to find rvl_cdip_dataset.csv? #24

Closed SaynaEbrahimi closed 2 years ago

SaynaEbrahimi commented 2 years ago

Hi,

Thank you for sharing your great work. Can you please also share your rvl_cdip_dataset.csv file or refer me to where I can find it?

Thanks, Sayna

uakarsh commented 2 years ago

Hi Sayna,

That was a test file, and I don't think, we would be able to share it, since it had some issues. But, I can give you a general idea, about how to use the DocFormer for your particular task at hand.

I have mentioned it here, all you need to do is, download any of the document images dataset, containing/not containing labels (For unsupervised work), and then follow the steps here,

https://github.com/shabie/docformer/issues/23

Hope this helps, and do let us know if you need any more information.

uakarsh commented 2 years ago

Maybe, if the issue has been resolved, can we close this issue?