KIE on wildreceipt dataset

[riyajatar93]

I am trying to use KIE on wildreceipt dataset.
from this link
https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_en/algorithm_kie_sdmgr_en.md

but why i need a ground truth label during inference?
shouldn't we pass the output of text detection and text recognition to KIE model as input ?

python3 tools/infer_kie.py -c configs/kie/kie_unet_sdmgr.yml -o Global.checkpoints=kie_vgg16/best_accuracy Global.infer_img=./train_data/wildreceipt/1.txt

I will appreciate your help , i am stuck here

[jchain]

./train_data/wildreceipt/1.txt is not ground truth label. It contains the input image path and the output of text detection and recognition.