PaddlePaddle / PP-DocBlockLayout

huggingface.co
Total runs: 12.1K
24-hour runs: 0
7-day runs: 218
30-day runs: 3.3K
Model's Last Updated: July 22 2025
image-to-text

Introduction of PP-DocBlockLayout

Model Details of PP-DocBlockLayout

PP-DocBlockLayout

Introduction

A layout block localization model trained on a self-built dataset containing Chinese and English papers, PPT, multi-layout magazines, contracts, books, exams, ancient books and research reports using RT-DETR-L. The layout detection model includes 1 category: Region.

Model mAP(0.5) (%)
PP-DocBlockLayout 95.9

Note : the evaluation set of the above precision indicators is the self built version sub area detection data set, including Chinese and English papers, magazines, newspapers, research reports PPT、 1000 document type pictures such as test papers and textbooks.

Quick Start
Installation
  1. PaddlePaddle

Please refer to the following commands to install PaddlePaddle using pip:

# for CUDA11.8
python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/

# for CUDA12.6
python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/

# for CPU
python -m pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/

For details about PaddlePaddle installation, please refer to the PaddlePaddle official website .

  1. PaddleOCR

Install the latest version of the PaddleOCR inference package from PyPI:

python -m pip install paddleocr
Model Usage

You can quickly experience the functionality with a single command:

paddleocr layout_detection --model_name PP-DocBlockLayout -i https://cdn-uploads.huggingface.co/production/uploads/63d7b8ee07cd1aa3c49a2026/SCL4KLVcaUKkinua_bTec.png

You can also integrate the model inference of the LayoutDetection module into your project. Before running the following code, please download the sample image to your local machine.

from paddleocr import LayoutDetection

model = LayoutDetection(model_name="PP-DocBlockLayout")
output = model.predict("SCL4KLVcaUKkinua_bTec.png", batch_size=1, layout_nms=True)
for res in output:
    res.print()
    res.save_to_img(save_path="./output/")
    res.save_to_json(save_path="./output/res.json")

After running, the obtained result is as follows:

{'res': {'input_path': '/root/.paddlex/predict_input/SCL4KLVcaUKkinua_bTec.png', 'page_index': None, 'boxes': [{'cls_id': 0, 'label': 'Region', 'score': 0.9768685698509216, 'coordinate': [31.313992, 298.04843, 479.92798, 1994.14]}, {'cls_id': 0, 'label': 'Region', 'score': 0.9728955626487732, 'coordinate': [648.478, 1233.5554, 1552.8765, 1992.712]}, {'cls_id': 0, 'label': 'Region', 'score': 0.9725626707077026, 'coordinate': [647.51337, 295.63956, 1550.7095, 1181.5878]}, {'cls_id': 0, 'label': 'Region', 'score': 0.9079533219337463, 'coordinate': [644.75916, 59.31064, 1468.8861, 264.68124]}, {'cls_id': 0, 'label': 'Region', 'score': 0.8413463234901428, 'coordinate': [31.890125, 60.103912, 470.73123, 284.72952]}]}}

The visualized image is as follows:

image/jpeg

For details about usage command and descriptions of parameters, please refer to the Document .

Links

PaddleOCR Repo

PaddleOCR Documentation

Runs of PaddlePaddle PP-DocBlockLayout on huggingface.co

12.1K
Total runs
0
24-hour runs
2.0K
3-day runs
218
7-day runs
3.3K
30-day runs

More Information About PP-DocBlockLayout huggingface.co Model

More PP-DocBlockLayout license Visit here:

https://choosealicense.com/licenses/apache-2.0

PP-DocBlockLayout huggingface.co

PP-DocBlockLayout huggingface.co is an AI model on huggingface.co that provides PP-DocBlockLayout's model effect (), which can be used instantly with this PaddlePaddle PP-DocBlockLayout model. huggingface.co supports a free trial of the PP-DocBlockLayout model, and also provides paid use of the PP-DocBlockLayout. Support call PP-DocBlockLayout model through api, including Node.js, Python, http.

PaddlePaddle PP-DocBlockLayout online free

PP-DocBlockLayout huggingface.co is an online trial and call api platform, which integrates PP-DocBlockLayout's modeling effects, including api services, and provides a free online trial of PP-DocBlockLayout, you can try PP-DocBlockLayout online for free by clicking the link below.

PaddlePaddle PP-DocBlockLayout online free url in huggingface.co:

https://huggingface.co/PaddlePaddle/PP-DocBlockLayout

PP-DocBlockLayout install

PP-DocBlockLayout is an open source model from GitHub that offers a free installation service, and any user can find PP-DocBlockLayout on GitHub to install. At the same time, huggingface.co provides the effect of PP-DocBlockLayout install, users can directly use PP-DocBlockLayout installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

PP-DocBlockLayout install url in huggingface.co:

https://huggingface.co/PaddlePaddle/PP-DocBlockLayout

Url of PP-DocBlockLayout

PP-DocBlockLayout huggingface.co Url

Provider of PP-DocBlockLayout huggingface.co

PaddlePaddle
ORGANIZATIONS

Other API from PaddlePaddle

huggingface.co

Total runs: 588.6K
Run Growth: 37.6K
Growth Rate: 6.39%
Updated:July 22 2025
huggingface.co

Total runs: 393
Run Growth: 167
Growth Rate: 42.49%
Updated:July 22 2025