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.
Adding inference pipeline to detect, recognize, and extract tables from images. (Note that for text content to be included in the extraction, text words need to be provided as additional input, along with the image, to the pipeline.)
Adding inference pipeline to detect, recognize, and extract tables from images. (Note that for text content to be included in the extraction, text words need to be provided as additional input, along with the image, to the pipeline.)