Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.
MIT License
2.01k
stars
231
forks
source link
Bugfix when extracting tokens for multiple detected objects #184
Fixed a bug where the extraction of the word dir fails when there are multiple objects (tables) detected. This was because the token coordinates are shifted cumulatively for all the detected objects.
Fixed a bug where the extraction of the word dir fails when there are multiple objects (tables) detected. This was because the token coordinates are shifted cumulatively for all the detected objects.