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
553 stars 191 forks source link

normalize_relation_features #101

Open tkgw opened 2 years ago

tkgw commented 2 years ago

https://github.com/wenwenyu/PICK-pytorch/blob/8bd025bcc1a53e8520f0de12b5ea754359d57eee/data_utils/documents.py#L297

i assume it's appropriate to write it like this

            feat[:, :, i] = (feat[:, :, i] - min_value) / (max_value - min_value)