https://github.com/lpiwowar/table-recognition
GNN based program that extracts information (structure + data) form a table image.
https://github.com/lpiwowar/table-recognition
computer-vision table-recognition
Last synced: 5 months ago
JSON representation
GNN based program that extracts information (structure + data) form a table image.
- Host: GitHub
- URL: https://github.com/lpiwowar/table-recognition
- Owner: lpiwowar
- License: bsd-3-clause
- Created: 2022-01-28T23:08:40.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2023-07-26T18:00:06.000Z (almost 3 years ago)
- Last Synced: 2023-07-26T20:22:14.365Z (almost 3 years ago)
- Topics: computer-vision, table-recognition
- Language: Python
- Homepage:
- Size: 234 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Table recognition 🧠
====================
This repository contains a code for training and using a table recognition
model.
Video 🎞️
--------
Requirements
------------
- The tested was tested using ```python v3.7.12```
- To use the code please install the requirements first
```bash
# Installation of CPU packages
virtualenv .venv && source .venv/bin/activate
pip install -r requirements-cpu.txt
```
- To use or train the model using GPU it is necessary to install packages
listed in requirements-gpu.txt (to use this packages you have to have
```cuda 11.2``` installed on your system)
```bash
# Installation of GPU packages
virtualenv .venv && source .venv/bin/activate
pip install -r requirements-gpu.txt
```