search

microsoft / unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
https://aka.ms/GeneralAI
MIT License
20.13k stars 2.55k forks source link

Inference with LayoutXLM #895

Open bannima opened 2 years ago

bannima commented 2 years ago

should the layoutxlm model inference 2 times for key-value extraction? Hi there, I 'm using the LayoutXLM model for Document Understanding task in Medical Case Picture. In my situation, I should know the semantic entity recognition and relation extraction results as the same time. My question is the released layoutxlm code are separated for ser and re tasks in a pipeline format. So the layoutxlm should inference 2 times and separately for ser and re? Is there any joint model for two tasks at inference time so that we can put the data to layoutxlm just one time?

bannima commented 2 years ago

thanks in advance

githublsk commented 1 year ago

thanks in advance

Yes, just for two times