Inference with LayoutXLM

[bannima]

**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]

thanks in advance

[githublsk]

thanks in advance

Yes, just for two times