GNN-TableExtraction
GNN-TableExtraction copied to clipboard
Code for ICPR2022 paper: "Graph Neural Networks and Representation Embedding for table extraction in PDF Documents"
Greetings, Do we have to train both SOM and GMM while computing P prototypes? Or only one of them is sufficient? TIA
any instructions for getting labels with the current model?
could you please mention about the using the merge dataset to create features? I am able to merge the two datasets (PubTables1M and publaynet); but I am not able to...
it throws an error config['secret_token'] = secret["SAS_TOKEN_HERE"]. Please help me from here how to proceed.