Skip to content

cizhenshi/Rscup2019-Object-Detection-Track-3th-Solution

Folders and files

NameName
Last commit message
Last commit date

Latest commit

e2ffe1a · Aug 29, 2019
Jul 2, 2019
Aug 26, 2019
Nov 26, 2018
Aug 26, 2019
Jul 21, 2019
Aug 29, 2019
Jul 23, 2019
May 20, 2019
Jun 4, 2019
Jul 1, 2019
May 21, 2019
Jul 24, 2019
Jul 4, 2019
Jun 25, 2019
Jun 15, 2019
Jun 19, 2019
Aug 3, 2019
Aug 25, 2019
Aug 28, 2019
Jun 22, 2019
Jul 29, 2019
Aug 29, 2019
Jul 18, 2019
May 23, 2019
Jul 20, 2019
Aug 29, 2019
Jul 24, 2019

Repository files navigation

RSCUP2019 object detection track 3th solution

Introduction

2019遥感图像稀疏表征与智能分析竞赛第三名方案

Major tricks

  • Mask RCNN 0.3541
  • Hybrid Task RCNN + deform conv 0.36633
  • expand bbox 0.364
  • cascade score thresh adopt to 0.5 0.366
  • small number class augmentation 0.372
  • cross_entropy weighted 0.369
  • sync BN 0.376
  • IOU sampler 0.383
  • pesudo label fine tune 0.362
  • balanced sampler 0.369
  • augmentation 0.40
  • 3 scale test 0.399
  • resnext101 0.41
  • scale2 finetune 0.43

Installation

Please refer to INSTALL.md for installation and dataset preparation.

PrepareData

python ./tools/prepare_data.py OR Dataprepare.ipynb

data will generate in ./data/rscup/annotation/ and ./data/rscup/train

Train

./tools/dist_train.sh ./configs/rscup/htc_next_3s.py <gpu_num>

Test

./tools/dist_test.sh ./configs/rscup/htc_next_3s.py ./work_dirs/htc_next_3s/epoch*.pth <gpu_num> \

--out test.pkl

Merge_result

python ./tools/merge_result.py

Convert2caffe

We achieved the converter from Hybrid Task cascade RCNN trained with mmdetection to Caffe.

Please refer " ".

About

Rscup2019 Object Detection Track 3th Solution

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published