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

There is no SEP token appended #2

Closed shabie closed 3 years ago

shabie commented 3 years ago

You have a [SEP] or an equivalent token at the end which I think is not what the authors used:

https://github.com/shabie/docformer/blob/ae1ce38250d9e6ea2f9589fc11b43097045b2488/src/docformer/dataset.py#L260-L261

See the first paragraph of the sub-section "Language Features" in the section 3.1

uakarsh commented 3 years ago

You can check it now, I have updated it, and for the bounding boxes as well, I removed the [1000,1000,1000,1000]