Skip to content

Pytorch implementation of MRCNN for SceneClassification( Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs)

Notifications You must be signed in to change notification settings

joniea/MRCNN-for-Scene-Classification

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MRCNN

Pytorch implementation of MRCNN for SceneClassification.

We refer to the structure in paper Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs

Datasets and Pretrained Models

  1. datasets URL: https://pan.baidu.com/s/1j4pSD0--Elo0QyAkmSOcBg
ln -s $DOWNLOAD_PATH $MRCNN/data/
  1. pretrained models for extra network URL: https://pan.baidu.com/s/11O7FQLyYC81WX4h7-1MPvA
ln -s $DOWNLOAD_PATH $MRCNN/resnet/

3.pretrained model for MRCNN URL: https://pan.baidu.com/s/10b8coHP3RW9yX-uAPmTauA     Extract code: 0hrr

ln -s $DOWNLOAD_PATH $MRCNN/xq_model/

Train

cd $MRCNN/classification

run python train_MRCNN.py

Test

cd $MRCNN/classification

mkdir xq_result

run python val_MRCNN.py

About

Pytorch implementation of MRCNN for SceneClassification( Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%