This repository contains the Implementation details of the paper "DPED: Bio-inspired dual-pathway network for edge detection".
The address of the paper is at https://www.frontiersin.org/articles/10.3389/fbioe.2022.1008140/full
If you have any questions, you can make issue or send email to gauss.chenll@gmail.com.
If you are using the code/model/data provided here in a publication, please consider citing our paper:
@article{chen2022dped,
title={DPED: Bio-inspired dual-pathway network for edge detection},
author={Chen, Yongliang and Lin, Chuan and Qiao, Yakun},
journal={Frontiers in Bioengineering and Biotechnology},
volume={10},
year={2022},
publisher={Frontiers Media SA}
}
All results is evaluated Python 3.7 with PyTorch 1.8.1 and MATLAB R2018b.
You can run our model by following these steps:
- Download our code.
- prepare the dataset.
- Configure the environment.
- If Windows (Linux) system, please modify the dataset_path in Win_cfgs.yaml(Lin_cfgs.yaml).
- Run the "mian.py".
We use the links in RCF Repository (really thanks for that).
The augmented BSDS500, PASCAL VOC, and NYUD datasets can be downloaded with:
wget http://mftp.mmcheng.net/liuyun/rcf/data/HED-BSDS.tar.gz
wget http://mftp.mmcheng.net/liuyun/rcf/data/PASCAL.tar.gz
wget http://mftp.mmcheng.net/liuyun/rcf/data/NYUD.tar.gz
Multicue Dataset is Here:
https://drive.google.com/file/d/1-tyt_KyzlYc9APafdh5mHJzh2K_F2hM8/view?usp=sharing
When building our codeWe referenced the repositories as follow: