2019 Spring ENGN 2560 Computer Vision Final Project
Group Members: Ziwei Chen, Yang Jiao, Yiming Li
This repository is highly based on Xuanyi Li's RCF PyTorch project. Thanks a lot!
The project relys on RCF. Please consider citing:
@article{RcfEdgePami2019, author = {Yun Liu and Ming-Ming Cheng and Xiaowei Hu and Jia-Wang Bian and Le Zhang and Xiang Bai and Jinhui Tang}, title = {Richer Convolutional Features for Edge Detection}, year = {2019}, journal= {IEEE Trans. Pattern Anal. Mach. Intell.}, volume={}, number={}, pages={}, doi = {}, }
@inproceedings{RCFEdgeCVPR2017, title={Richer Convolutional Features for Edge Detection}, author={Yun Liu and Ming-Ming Cheng, Xiaowei Hu and K Wang and X Bai}, booktitle={IEEE CVPR}, year={2017}, }
Install pytorch. The code is tested under 0.4.1 GPU version and Python 3.6 on Ubuntu 16.04. There are also some dependencies for a few Python libraries for data processing and visualizations like cv2 etc. It's highly recommended that you have access to GPUs.
For dataset used in this project, please refer to data_organize.md
To train a RCF model on BSDS500:
python train_RCF.py
Or on Brown CCV:
sbatch train.sh
We use BSDS-500 and its benchmark software for evalutaion.
Before evaluation, the non-maximum suppression must be perform. Refer to nms_pipeline for detailed instruction.
Our code is released under MIT License (see LICENSE file for details).
- To download the pretrained model, please click https://drive.google.com/open?id=1TupHeoBKawrniDka0Hc64m3BG4OKG8nM (This pretrained model is not the best model, just for communicating)
[1] Richer Convolutional Features for Edge Detection
[2] HED