Ziyi Yang

Hi @hammer, thanks for your interest in UDOP. We've released the encoder + text decoder model weights at https://huggingface.co/ZinengTang/Udop. By ""Due to fake document...", we mean that we need to...

Thanks again for your interest in our work. Here's an example of how UDOP works on an actual document: https://github.com/microsoft/i-Code/blob/main/i-Code-Doc/example_io.ipynb Thanks.

Hi, thanks for the interest in our work. The inference script is just merged: https://github.com/microsoft/i-Code/pull/50.

Thanks. We're working to release the model ckpt and the inference script.

Hi, thanks for the interest in our work. The inference script is just merged: https://github.com/microsoft/i-Code/pull/50.

Hi, I solve by I editing the config.py as follows: POVRAY_BINARY = path/to/povray/binary https://github.com/Zulko/vapory/issues/18

UDOP currently is English-only. To fully replicate this work on multilingual domain, you will need multilingual documents with OCR annotations, and labeled multilingual document for supervised pretraining.