File size: 365 Bytes
5da3e0d
 
 
bf136d4
5da3e0d
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
# The finetuned LayoutXLm model on Czech dataset for Visual Question Answering

The original model can be found [here](microsoft/layoutxlm-base)

The CIVQA dataset  is the Czech Invoice dataset for Visual Question Answering

Achieved results:

      eval_answer_text_recall = 0.7065
  
      eval_answer_text_f1 = 0.6998
 
      eval_answer_text_precision = 0.7319