# CRAFT-Reimplementation

**Repository Path**: zhangzzh2019/CRAFT-Reimplementation

## Basic Information

- **Project Name**: CRAFT-Reimplementation
- **Description**: CRAFT-Pyotorch：Character Region Awareness for Text Detection Reimplementation for Pytorch
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: craft
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-12-13
- **Last Updated**: 2021-12-13

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# CRAFT-Reimplementation
# Note：If you have any problems, please comment. Or you can join us weChat group. The QR code will update in issues #49 .
# 非常抱歉，一直没有继续维护这个工程，近期看到挺多人关注的，我预计11月底最晚12月初重新维护一下工程，由于当时实习期间整体工程能力不够导致工程相对较乱，这个重新维护会整理清楚。维护周期大概是两周时间，我会重新整理code以及重新训练同时上传训练的pretrain model。同时一些实验的关键和实验思路我会写上注释，欢迎到时关注。

## Reimplementation：Character Region Awareness for Text Detection Reimplementation based on Pytorch

## Character Region Awareness for Text Detection
Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee
(Submitted on 3 Apr 2019)

The full paper is available at: https://arxiv.org/pdf/1904.01941.pdf                                                         

## Install Requirements:                                                                                                        
1、PyTroch>=0.4.1                                                                                                                             
2、torchvision>=0.2.1 			                                                    																			                             
3、opencv-python>=3.4.2                                                                                                       
4、check requiremtns.txt                                                                                                      
5、4 nvidia GPUs(we use 4 nvidia titanX)                                                                                      


# to do list
Release strong supervision training part in early December