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
255 stars 40 forks source link

Do you have a plan for pre-trained model and inference code? #25

Closed yellowjs0304 closed 2 years ago

yellowjs0304 commented 2 years ago

HI, Thank you for sharing nice work.

I'm new in Document Understanding, I wanna check the inference on FUNSD dataset. Could you share any pre-trained models, and inference code?

:) i'm waiting your reply. thank you.

uakarsh commented 2 years ago

For the training part, here is the link, which might help you, https://github.com/shabie/docformer/issues/23

As for the model, we have to wait for some time, as the dataset used by the authors is yet unknown (based on a sampling of the different classes and so on), but I guess the link above might help you, give an idea about the training procedure. I would surely add the code for training shortly.

Hope it helps, and do let us know if there are more queries.

Regards, Akarsh

yellowjs0304 commented 2 years ago

Thank you for fast reply. I understand what you told. But, what i really wanted is only the inference, because i don't have enough resources for training 😥 I would appreciate it if you could consider a method for this part as well.

Sincerely.