Skip to content
/ MGAN Public

Mask-Guided Attention Network for Occluded Pedestrian Detection. (ICCV'19)

Notifications You must be signed in to change notification settings

Leotju/MGAN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Mask-Guided Attention Network for Occluded Pedestrian Detection

Pedestrian detection framework as detailed in arXiv report, accepted to ICCV 2019.

Installation

Our MGAN is based on mmdetection. Please check INSTALL.md for installation instructions.

Datasets

You can download CityScapes Datasets.Put it in data folder.

Testing

The following commands will test the model on 1 GPU.

python tools/test.py city_cfgs/mgan_50_65.py models/50_65.pth --out result/50_65.pkl

Eval

The following command will evaltate the results on CityPersons

python eval/eval_demo.py

Results

R HO Download
11.0 50.3 Google Drive/ Baidu Yun(zq93)

About

Mask-Guided Attention Network for Occluded Pedestrian Detection. (ICCV'19)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published