---
title: SLANeXt_wired_safetensors
canonical_url: "https://www.modelscope.cn/models/PaddlePaddle/SLANeXt_wired_safetensors"
md_url: "https://www.modelscope.cn/models/PaddlePaddle/SLANeXt_wired_safetensors.md"
repository: PaddlePaddle/SLANeXt_wired_safetensors
last_updated: 2026-04-15
license: apache-2.0
model_type:
  - slanext
parameters: 90.9M
tensor_type:
  - F32
  - F16
library_name:
  - transformer
  - safetensors
language:
  - en
  - zh
downloads: 243
stars: 0
tags:
  - OCR
  - PaddlePaddle
  - PaddleOCR
  - table_structure_recognition
---

# SLANeXt_wired_safetensors

> SLANeXt_wired_safetensors - PaddlePaddle 在 ModelScope 开源的模型。Table structure recognition is an important component of table recognition systems, capable of converting non-editable table images into editable table formats (such as HTML). The goal of table…

PaddlePaddle/SLANeXt_wired_safetensors 是 ModelScope 魔搭社区上的 90.9M 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: PaddlePaddle/SLANeXt_wired_safetensors
- **License**: apache-2.0
- **Parameters**: 90.9M
- **Tags**: OCR, PaddlePaddle, PaddleOCR, table_structure_recognition
- **Downloads**: 243
- **Stars**: 0
- **Last updated**: 2026-04-15

Source: https://www.modelscope.cn/models/PaddlePaddle/SLANeXt_wired_safetensors

---

# SLANeXt_wired

## Introduction

Table structure recognition is an important component of table recognition systems, capable of converting non-editable table images into editable table formats (such as HTML). The goal of table structure recognition is to identify the positions of rows, columns, and cells in tables. The performance of this module directly affects the accuracy and efficiency of the entire table recognition system. The table structure recognition module usually outputs HTML code for the table area, which is then passed as input to the tabl recognition pipeline for further processing.

<table>
<tr>
<th>Model</th>
<th>Accuracy (%)</th>
<th>GPU Inference Time (ms)<br/>[Normal Mode / High Performance Mode]</th>
<th>CPU Inference Time (ms)<br/>[Normal Mode / High Performance Mode]</th>
<th>Model Storage Size (M)</th>
</tr>
<tr>
<td>SLANeXt_wired</td>
<td>69.65</td>
<td>--</td>
<td>--</td>
<td>351M</td>
</tr>
</table>

**Note**: The accuracy of SLANeXt_wired comes from the results of joint testing with SLANeXt_wireless.

## Model Usage

```python
import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForTableRecognition

model_path="PaddlePaddle/SLANeXt_wired_safetensors"
model = AutoModelForTableRecognition.from_pretrained(model_path, dtype=torch.float32, device_map="auto")
image_processor = AutoImageProcessor.from_pretrained(model_path)

image = Image.open(requests.get("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/table_recognition.jpg", stream=True).raw)
inputs = image_processor(images=image, return_tensors="pt").to(model.device)
outputs = model(**inputs)

results = image_processor.post_process_table_recognition(outputs)

print(result['structure'])
print(result['structure_score'])
```