Udop Large 512

🚀 UDOP model

The UDOP model unifies vision, text, and layout for universal document processing, offering solutions for various document AI tasks.

🚀 Quick Start

The UDOP model was proposed in Unifying Vision, Text, and Layout for Universal Document Processing by Zineng Tang, Ziyi Yang, Guoxin Wang, Yuwei Fang, Yang Liu, Chenguang Zhu, Michael Zeng, Cha Zhang, Mohit Bansal.

✨ Features

UDOP adopts an encoder - decoder Transformer architecture based on T5 for document AI tasks like document image classification, document parsing and document visual question answering.

📚 Documentation

Intended uses & limitations

You can use the model for document image classification, document parsing and document visual question answering (DocVQA).

How to use

Here's how to use the model for one - shot semantic segmentation:

from transformers import AutoProcessor, UdopForConditionalGeneration
from datasets import load_dataset

# load model and processor
# in this case, we already have performed OCR ourselves
# so we initialize the processor with `apply_ocr=False`
processor = AutoProcessor.from_pretrained("microsoft/udop-large", apply_ocr=False)
model = UdopForConditionalGeneration.from_pretrained("microsoft/udop-large")

# load an example image, along with the words and coordinates
# which were extracted using an OCR engine
dataset = load_dataset("nielsr/funsd-layoutlmv3", split="train")
example = dataset[0]
image = example["image"]
words = example["tokens"]
boxes = example["bboxes"]
question = "Question answering. What is the date on the form?"

# prepare everything for the model
encoding = processor(image, question, words, boxes=boxes, return_tensors="pt")

# autoregressive generation
predicted_ids = model.generate(**encoding)
print(processor.batch_decode(predicted_ids, skip_special_tokens=True)[0])
9/30/92

Refer to the demo notebooks for fine - tuning/inference.

BibTeX entry and citation info

@misc{tang2023unifying,
      title={Unifying Vision, Text, and Layout for Universal Document Processing}, 
      author={Zineng Tang and Ziyi Yang and Guoxin Wang and Yuwei Fang and Yang Liu and Chenguang Zhu and Michael Zeng and Cha Zhang and Mohit Bansal},
      year={2023},
      eprint={2212.02623},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

📄 License

This project is licensed under the MIT license.