Skip to content

shnew/R2IPoints

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

78 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

R2IPoints : Pursuing Rotation-Insensitive Point Representation for Aerial Object Detection

Codes for R2IPoints : Pursuing Rotation-Insensitive Point Representation for Aerial Object Detection.

The overview of R2IPoints:

overview

Getting Started

Prerequisties

  • pip install torch==1.1.0
  • pip install torchvision==0.3.0
  • pip install mmdet==1.2.0
  • pip install mmcv==0.3.1
  • pip install -r requirements/build.txt
  • pip install -v -e .

Datasets preparation

Quick start

  • python tools/train.py ./configs/R2IPoints/R2IPoints_moment_r101_fpn_2x_DIOR.py
  • python tools/test.py ./configs/R2IPoints/R2IPoints_moment_r101_fpn_2x_DIOR.py ${CHECKPOINT_FILE} --eval mAP

Pre-trained models

About

Codes for R2IPoints : Pursuing Rotation-Insensitive Point Representation for Aerial Object Detection.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published