Tools for extract figure, table, text,... from a pdf document.

• About the Project
  • Built With
• Getting Started
  • Prerequisites
  • Installation

• Detectron2
• Streamlit
• Python3
• Flask

Make sure you have python3 installed on your computer. Recommended to install on Ubuntu.

To get a local copy up and running follow these simple steps.

This is an example of how to list things you need to use the software and how to install them.

• Detectron2

Requirment

• CUDA=10.1
• Pytorch >= 1.7.0

How to install CUDA 10.1 can be found here: https://developer.nvidia.com/cuda-10.1-download-archive-base

How to install Pytorch can be found here: https://pytorch.org/

After installed above package, follow the instructions below to install detectron2:

$   pip install cython pyyaml==5.1
$   pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu100/index.html

After installed detectron2, run:

$   pip install -r requirments.txt

1. Clone the repo

git clone https://github.com/Wild-Rift/Document-Layout-Analysis.git

2. Run demo

streamlit run virtualize.py