M

table-transformer-structure-recognition

Visionby Microsoft·Model page

Microsoft's 28M-parameter object detection model that recognizes table structure and cell boundaries in document images.

Share:

Model Card

Table Transformer (DETR) model trained on PubTables1M. It was introduced in the paper PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents by Smock et al. and first released in this repository.

Disclaimer: The team releasing Table Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

The Table Transformer is equivalent to DETR, a Transformer-based object detection model. Note that the authors decided to use the "normalize before" setting of DETR, which means that layernorm is applied before self- and cross-attention.

Usage

You can use the raw model for detecting the structure (like rows, columns) in tables. See the documentation for more info.

Author
M
Microsoft
Organization · ✓
microsoft
Details
Downloads1.2M
Likes219
AccessOpen Source
Taskobject-detection
Parameters29M
Licensemit
Librarytransformers
CreatedOct 14, 2022
UpdatedSep 6, 2023
View on Hugging Face
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

table-transformer-structure-recognition — AI Model Details | Applied