利用Paddle框架复现CRAFT

Overview

CRAFT-Paddle

利用Paddle框架复现CRAFT

CRAFT

本项目基于paddlepaddle框架复现CRAFT,并参加百度第三届论文复现赛,将在2021年5月15日比赛完后提供AIStudio链接~敬请期待

参考项目:

CRAFT: Character-Region Awareness For Text detection

项目配置

pip install -r requirements.txt

你应该具有以下目录

/home/aistudio/CRAFT(工程目录)
/home/aistudio/Data(数据集文件)

数据集文件已挂载,自行解压即可

训练

The code for training is not included in this repository, and we cannot release the full training code for IP reason.

作者并未提供训练代码

权重转换

这里用到了X2Paddle神器,转换代码如下,具体使用文档参见X2Paddle

from craft import CRAFT
import torch
from collections import OrderedDict
import imgproc
import numpy as np
import cv2

def copyStateDict(state_dict):
    if list(state_dict.keys())[0].startswith("module"):
        start_idx = 1
    else:
        start_idx = 0
    new_state_dict = OrderedDict()
    for k, v in state_dict.items():
        name = ".".join(k.split(".")[start_idx:])
        new_state_dict[name] = v
    return new_state_dict

# 构建输入
input_data = np.random.rand(1, 3, 736, 1280).astype("float32")
net = CRAFT()
net.load_state_dict(copyStateDict(torch.load('craft_mlt_25k.pth')))
net = net.cuda()
net.eval()

# 进行转换
from x2paddle.convert import pytorch2paddle
pytorch2paddle(net, 
          save_dir="paddlemodel", 
          jit_type="trace", 
          input_examples=[torch.tensor(input_data).cuda()])

完成后你会出现如下文件目录

/home/aistudio/CRAFT/paddlemodel
└───inference_model
└──────model.pdiparams
└──────model.pdiparams.info
└──────model.pdmodel
└───model.pdparams
└───x2paddle_code.py

使用同样的方式转换refinenet

测试

模型下载

提取码:4yy1

AIStudio链接

cd /home/aistudio/CRAFT
python test.py

Model name Used datasets Languages Purpose Model Link
General SynthText, IC13, IC17 Eng + MLT For general purpose craft_mlt_25k
IC15 SynthText, IC15 Eng For IC15 only craft_ic15_20k
LinkRefiner CTW1500 - Used with the General Model craft_refiner_CTW1500

下图是实际测试效果

评估

可以采用以下代码进行评估

cd /home/aistudio/CRAFT
python eval.py
cd /home/aistudio/CRAFT/outputs/submit_ic15/
zip ../submit_ic15.zip *
cd /home/aistudio/CRAFT/eval
`./eval_ic15.sh` or `bash eval_ic15.sh`
Method Dataset Backbone refiner Precision (%) Recall (%) F-measure (%) Model
basenet ICDAR2015 VGG16_BN N 82.2 77.9 80.0 craft_ic15_20k
basenet ICDAR2015 VGG16_BN N 85.1 79.4 82.2 craft_mlt_25k
basenet ICDAR2015 VGG16_BN Y 61.9 45.1 52.2 craft_ic15_20k
basenet ICDAR2015 VGG16_BN Y 63.1 43.3 51.4 craft_mlt_25k

评估total_text数据集可参见我的PSNET项目eval文件价下的评估代码

关于作者

姓名 郭权浩
学校 电子科技大学研2020级
研究方向 计算机视觉
主页 Deep Hao的主页
如有错误,请及时留言纠正,非常蟹蟹!
后续会有更多论文复现系列推出,欢迎大家有问题留言交流学习,共同进步成长!
Owner
QuanHao Guo
master at UESTC
QuanHao Guo
Autonomous Driving project for Euro Truck Simulator 2

hope-autonomous-driving Autonomous Driving project for Euro Truck Simulator 2 Video: How is it working ? In this video, the program processes the imag

Umut Görkem Kocabaş 36 Nov 06, 2022
A tensorflow implementation of EAST text detector

EAST: An Efficient and Accurate Scene Text Detector Introduction This is a tensorflow re-implementation of EAST: An Efficient and Accurate Scene Text

2.9k Jan 02, 2023
Document manipulation detection with python

image manipulation detection task: -- tianchi function image segmentation salie

JiaKui Hu 3 Aug 22, 2022
Balabobapy - Using artificial intelligence algorithms to continue the text

Balabobapy - Using artificial intelligence algorithms to continue the text

qxtony 1 Feb 04, 2022
Introduction to image processing, most used and popular functions of OpenCV

👀 OpenCV 101 Introduction to image processing, most used and popular functions of OpenCV go here.

Vusal Ismayilov 3 Jul 02, 2022
Code for AAAI 2021 paper: Sequential End-to-end Network for Efficient Person Search

This repository hosts the source code of our paper: [AAAI 2021]Sequential End-to-end Network for Efficient Person Search. SeqNet achieves the state-of

Zj Li 218 Dec 31, 2022
A simple demo program for using OpenCV on Android

Kivy OpenCV Demo A simple demo program for using OpenCV on Android Build with: buildozer android debug deploy run Run (on desktop) with: python main.p

Andrea Ranieri 13 Dec 29, 2022
aardio的opencv库

opencv_aardio dll库下载地址:https://github.com/xuncv/opencv-plugin/releases import cv2 img = cv2.imread("./images/Lena.jpg",1) img = cv2.medianBlur(img,5)

71 Dec 31, 2022
A bot that extract text from images using the Tesseract OCR.

Text from image (OCR) @ocr_text_bot A simple bot to extract text from images. Usage What do I need? A AWS key configured locally, see here. NodeJS. I

Weverton Marques 4 Aug 06, 2021
This is a passport scanning web service to help you scan, identify and validate your passport created with a simple and flexible design and ready to be integrated right into your system!

Passport-Recogniton-System This is a passport scanning web service to help you scan, identify and validate your passport created with a simple and fle

Mo'men Ashraf Muhamed 7 Jan 04, 2023
Official implementation of Character Region Awareness for Text Detection (CRAFT)

CRAFT: Character-Region Awareness For Text detection Official Pytorch implementation of CRAFT text detector | Paper | Pretrained Model | Supplementary

Clova AI Research 2.5k Jan 03, 2023
Generate text images for training deep learning ocr model

New version release:https://github.com/oh-my-ocr/text_renderer Text Renderer Generate text images for training deep learning OCR model (e.g. CRNN). Su

Qing 1.2k Jan 04, 2023
This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

TransFG: A Transformer Architecture for Fine-grained Recognition Official PyTorch code for the paper: TransFG: A Transformer Architecture for Fine-gra

Ju He 307 Jan 03, 2023
Natural language detection

Detect the language of text. What’s so cool about franc? franc can support more languages(†) than any other library franc is packaged with support for

Titus 3.8k Jan 02, 2023
Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

Convolutional Recurrent Neural Network This software implements the Convolutional Recurrent Neural Network (CRNN), a combination of CNN, RNN and CTC l

Baoguang Shi 2k Dec 31, 2022
Character Segmentation using TensorFlow

Character Segmentation Segment characters and spaces in one text line,from this paper Chinese English mixed Character Segmentation as Semantic Segment

26 Aug 25, 2022
Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

This is the official implementation of "Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation". For more details, please

Pengyuan Lyu 309 Dec 06, 2022
Hand Detection and Finger Detection on Live Feed

Hand-Detection-On-Live-Feed Hand Detection and Finger Detection on Live Feed Getting Started Install the dependencies $ git clone https://github.com/c

Chauhan Mahaveer 2 Jan 02, 2022
A Joint Video and Image Encoder for End-to-End Retrieval

Frozen️ in Time ❄️ ️️️️ ⏳ A Joint Video and Image Encoder for End-to-End Retrieval (arXiv) Repository to contain the code, models, data for end-to-end

225 Dec 25, 2022
The project is an official implementation of our paper "3D Human Pose Estimation with Spatial and Temporal Transformers".

3D Human Pose Estimation with Spatial and Temporal Transformers This repo is the official implementation for 3D Human Pose Estimation with Spatial and

Ce Zheng 363 Dec 28, 2022