TableBank Word Test problem

DevashishPrasad / CascadeTabNet

This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"

MIT License

1.46k stars 422 forks source link

TableBank Word Test problem #108

Open linhongxiang opened 3 years ago

linhongxiang commented 3 years ago

I train the model on the TableBank Word Data ,and test. I got the the metrics's value 0.9337534861524578 0.9521966753595674 0.9428849004227591 which are worse than results 94.35 95.49 94.92 the paper gived.

RitwickJoshi commented 3 years ago

metric values are multiplied by 100 to get the percentage like 0.933753 * 100 = 93.37 which is not exact but close to 94.35 which was given in the paper