search

wenwenyu / PICK-pytorch

Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)
https://arxiv.org/abs/2004.07464
MIT License
556 stars 193 forks source link

A question about test #2

Closed courao closed 4 years ago

courao commented 4 years ago

When testing, do we have to provide boxes and texts(scripts?) of the test images?

wenwenyu commented 4 years ago

@courao Surely. Usually, the boxes and texts (transcripts ) of documents are obtained by the OCR system including text detection and recognition. When you get transcripts and boxes, all you need to know is how to prepare the testing data correctly. You can refer to data/README.md file for detail about data format.

wenwenyu commented 4 years ago

I am going to close this issue due to no response. Please feel free to reopen or create a new one if you have more questions.