facebookresearch / nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents
https://facebookresearch.github.io/nougat/
MIT License
8.81k stars 561 forks source link

nougat DocVQA #129

Closed DhavalWI closed 1 year ago

DhavalWI commented 1 year ago

as said nougat is similar in architecture to Donut. How do we create the docvqa model which donut has showed to be the best at using nougat?

Can you please help me in the right direction?

NielsRogge commented 1 year ago

See my notebooks here: https://github.com/NielsRogge/Transformers-Tutorials/tree/master/Donut/DocVQA

DhavalWI commented 1 year ago

See my notebooks here: https://github.com/NielsRogge/Transformers-Tutorials/tree/master/Donut/DocVQA

Thanks for the help. I will definitely try this one out.