FazBrowse GitHub Viewer | Trending | | Home

Tools: [Download Repo ZIP] [Original HTTPS Page]

jiangnanboy/table_structure_recognition: 利用Swin-Unet(Swin Transformer Unet)实现对文档图片里表格结构的识别，Swin-unet (Swin Transformer Unet) is used to identify the document table structure · GitHub

Name		Name	Last commit message	Last commit date
.idea		.idea
img		img
layers		layers
train_data		train_data
LICENSE		LICENSE
README.en.md		README.en.md
README.md		README.md
__init__.py		__init__.py
image.py		image.py
metrics.py		metrics.py
model.py		model.py
requirements.txt		requirements.txt
table_line_infer.py		table_line_infer.py
train.py		train.py
utils.py		utils.py

Repository files navigation

English | 简体中文

利用Swin-Unet(Swin Transformer Unet)实现对文档图片里表格结构的识别

实现功能

识别表格中的线条
结果转为excel

下载weights模型文件

模型文件地址: 链接：https://pan.baidu.com/s/1K2bxqqmZaOtPI1jeWN3Ygg

提取码：w0yj

拷贝model.h5文件到model目录下

训练（tensorflow2.5版本训练）

见本项目中的train.py

预测

见本项目中的table_line_infer.py

识别结果展示

表格线检测

表格线检测

表格线检测

表格线检测

表格线检测

表格线检测

contact

1、github：https://github.com/jiangnanboy

2、blog：https://www.cnblogs.com/little-horse/

3、QQ:2229029156

About

利用Swin-Unet(Swin Transformer Unet)实现对文档图片里表格结构的识别，Swin-unet (Swin Transformer Unet) is used to identify the document table structure

swin-transformer-unet swin-unet table-recognition table-structure-recognition

27 stars

1 watching

Report repository

Releases

Packages

Used by

Contributors

Languages

Back | FazBrowse Home | New Git URL