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

Input shape resnet50 in PICK #79

Open trongnghia05 opened 3 years ago

trongnghia05 commented 3 years ago

As far as I know the input of resnet50 is 224x224 but when I test it seems PICK changes the input option of this model, can someone explain to me, I'm new to computer vision, feel thanks.