README.md

---
license: apache-2.0
library_name: PaddleOCR
language:
- en
- zh
pipeline_tag: image-to-text
tags:
- OCR
- PaddlePaddle
- PaddleOCR
- layout_detection
---

# 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.

## Model Usage

### Install Dependencies

```shell
pip install -U paddleocr
pip install -U onnxruntime-gpu
```

### CLI Usage

```shell
paddleocr layout_detection -i ./demo.jpg --model_name PP-DocBlockLayout --engine onnxruntime
```

### Python API Usage

```python
from paddleocr import LayoutDetection

model = LayoutDetection(
    model_name="PP-DocBlockLayout",
    engine="onnxruntime",
)
output = model.predict("./demo.jpg", batch_size=1)
for res in output:
    res.print()
    res.save_to_img(save_path="./output/")
    res.save_to_json(save_path="./output/res.json")
```