table transformer structure recognition

Providermicrosoft
Categoryobject-detection
Licensemit
Downloads1.2K
Stars0

Overview

Table Transformer (TATR) is a specialized object detection model designed to automate the structural analysis of tables within document images. Unlike generic OCR, it focuses on identifying the spatial hierarchy of table components, specifically isolating table boundaries and recognizing individual rows and columns. For developers building document parsing pipelines or automated data extraction tools, this model serves as a critical pre-processing step to convert unstructured visual tables into machine-readable formats. It integrates well into existing computer vision workflows and offers a robust alternative to rule-based heuristic parsing, providing better generalization across diverse document layouts.

Highlights

  • Accurately detects table boundaries and internal cell structures
  • Optimized for converting document images into structured data
  • MIT license allows for flexible commercial integration
  • Reduces reliance on fragile, rule-based layout heuristics

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("microsoft/table-transformer-structure-recognition")
tokenizer = AutoTokenizer.from_pretrained("microsoft/table-transformer-structure-recognition")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download microsoft/table-transformer-structure-recognition

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download microsoft/table-transformer-structure-recognition config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('microsoft/table-transformer-structure-recognition')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/microsoft/table-transformer-structure-recognition

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/microsoft/table-transformer-structure-recognition

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('microsoft/table-transformer-structure-recognition')
tokenizer = AutoTokenizer.from_pretrained('microsoft/table-transformer-structure-recognition')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model microsoft/table-transformer-structure-recognition

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model microsoft/table-transformer-structure-recognition README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('microsoft/table-transformer-structure-recognition')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/microsoft/table-transformer-structure-recognition.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/microsoft/table-transformer-structure-recognition.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'microsoft/table-transformer-structure-recognition')

Full Documentation

来源: HuggingFace

---
license: mit
widget:

  • src: https://documentation.tricentis.com/tosca/1420/en/content/tbox/images/table.png

example_title: Table
---

Table Transformer (fine-tuned for Table Structure Recognition)

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.

View official source
Join our Telegram