Skip to content
/ LCFCN Public
forked from ServiceNow/LCFCN

ECCV 2018 - Where are the Blobs: Counting by Localization with Point Supervision

License

Notifications You must be signed in to change notification settings

alzayats/LCFCN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LCFCN - ECCV 2018

Where are the Blobs: Counting by Localization with Point Supervision

[Paper][Video]

Requirements

  • Pytorch version 0.4 or higher.

Description

Given a test image, the trained model outputs blobs in the image, then counts the number of predicted blobs (see Figure below).

Shanghai test image

Running the saved models

  1. Download the checkpoints,
bash checkpoints/download.sh
  1. Output the saved results,
python main.py -m summary -e trancos
  1. Re-evaluate the saved model,
python main.py -m test -e trancos

Training the models from scratch

To train the model,

python main.py -m train -e trancos

Benchmark

Method Trancos Pascal
ResFCN 3.39 0.31
Paper 3.32 0.31

Citation

If you find the code useful for your research, please cite:

@Article{laradji2018blobs,
    title={Where are the Blobs: Counting by Localization with Point Supervision},
    author={Laradji, Issam H and Rostamzadeh, Negar and Pinheiro, Pedro O and Vazquez, David and Schmidt, Mark},
    journal = {ECCV},
    year = {2018}
}

About

ECCV 2018 - Where are the Blobs: Counting by Localization with Point Supervision

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.2%
  • Shell 1.8%