microsoft/table-transformer
table-transformer
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.
Builder
Microsoft
microsoft • big-tech
Stars
2,884
Using upstream star count
Forks
311
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
May 17, 2021
Project creation date
README Summary
Table Transformer (TATR) is a deep learning model designed to extract and structure tables from unstructured documents including PDFs and images. This repository serves as the official source for the PubTables-1M dataset, which contains over one million annotated tables, and includes the GriTS evaluation metric for assessing table structure recognition performance. The model uses transformer architecture to detect table boundaries and extract their structural elements for downstream processing.
AI Dev Skills
Unmapped
Tags
Taxonomy
Deployment Context
Industries
Skill Areas
Recent Activity
Updated 1 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
PM Skills
Languages
Timeline
- Project created
- May 17, 2021
- Forked
- Mar 23, 2026
- Your last push
- 1 years ago
- Upstream last push
- 1 years ago
- Tracked since
- Jun 24, 2024
Similar Repos
pgvector cosine similarity · $0
Loading…