Home

Awesome

DSACA

Code release for Dilated-Scale-Aware Category-Attention ConvNet for Multi-Class Object Counting (Accepted)

Image text

Changelog

Requirements

Pre trained model

VisDrone_class8.pth and RSOC_class2.pth download.

Data

  -/DSACA-main
      -/DSACA-main/dataset
         └─── VisDrone
            └───VisDrone2019-DET-train
            └───VisDrone2019-DET-val
         └─── RSOC
            └───train
            └───val
            └───test_large-vehicle.txt
            └───test_ship.txt
            └───test_small-vehicle.txt
            └───train_large-vehicle.txt
            └───train_ship.txt
            └───train_small-vehicle.txt
      -/DSACA-main/pre_trained
         └─── VisDrone_class8.pth
         └─── RSOC_class2.pth
         └─── pre_trained.md
      -/DSACA-main/density_generate
         └─── RSOC_choose.py
         └─── VisDrone.py
         └─── RSOC.py
      -/DSACA-main/make_npydata
         └─── VisDrone_make_npydata.py
         └─── RSOC_make_npydata.py
      -/DSACA-main/Network
         └─── VisDrone_class8.py
         └─── baseline_DSAM_CAM.py
      -/DSACA-main/images
         └─── intro.png
      └─── config.py
      └─── dataset.py
      └─── image.py
      └─── utils.py
      └─── VisDrone_train_class8_CAM_DSAM.py
      └─── RSOC_train_class2_CAM_DSAM.py
      └─── README.md

Train & Test

Contact

Thanks for your attention! If you have any suggestion or question, you can leave a message here or contact us directly: