poloclub/tsr-convstem
High-Performance Transformers for Table Structure Recognition Need Early Convolutions
This project helps convert tables from image formats, like those in scanned documents or PDFs, into a machine-readable format such as HTML. You input an image containing a table, and it outputs the table's structure, recognizing cells, rows, and columns. This is ideal for data entry specialists, researchers, or anyone who needs to extract structured data from visual documents quickly and accurately.
No commits in the last 6 months.
Use this if you need to efficiently and accurately convert tables embedded in images or documents into a structured, editable format.
Not ideal if you primarily work with already digital, machine-readable tables (e.g., CSV, Excel) and don't need to process them from images.
Stars
45
Forks
4
Language
Python
License
MIT
Category
Last pushed
Apr 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/poloclub/tsr-convstem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
VectorInstitute/odyssey
A toolkit for developing foundation models using Electronic Health Record (EHR) data.
ycq091044/BIOT
BIOT - A framework for pretraining biosignals at scale. Large EEG pre-trained models.
AntixK/PyTorch-Model-Compare
Compare neural networks by their feature similarity
woodRock/fishy-business
Machine Learning for Rapid Evaporative Ionization Mass Spectrometry for Marine Biomass Analysis...
soda-inria/carte
Repository for CARTE: Context-Aware Representation of Table Entries