https://github.com/FakerYFX/FOTS

An Implementation of the FOTS: Fast Oriented Text Spotting with a Unified Network
https://github.com/FakerYFX/FOTS

Last synced: 10 days ago
JSON representation

An Implementation of the FOTS: Fast Oriented Text Spotting with a Unified Network

• Host: GitHub
• URL: https://github.com/FakerYFX/FOTS
• Owner: FakerYFX
• Created: 2018-11-08T07:14:08.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2018-11-08T07:17:16.000Z (about 6 years ago)
• Last Synced: 2024-10-20T13:36:40.493Z (24 days ago)
• Language: C++
• Size: 222 KB
• Stars: 173
• Watchers: 15
• Forks: 41
• Open Issues: 16
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# FOTS: Fast Oriented Text Spotting with a Unified Network

### Introduction

This is a pytorch re-implementation of [FOTS: Fast Oriented Text Spotting with a Unified Network](http://openaccess.thecvf.com/content_cvpr_2018/CameraReady/1699.pdf).

The features are summarized blow:

+ Only **detection** part is implemented.

### Contents

1. [Installation](#installation)

2. [Download](#download)

3. [Train](#train)

4. [Test](#test)

### Installation

1. Any version of torch version >= 0.3.1 should be ok.

### Download

1. Models trained on ICDAR 2015 (training set) + ICDAR 2017 (training set)

### Train

If you want to train the model, you should provide the dataset path, in the dataset path, a separate gt text file should be provided for each image

and run

```

python main_train.py

```

### Test

run

```

python eval.py

```

a text file will be then written to the output path.