Need help with gpnn?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

SiyuanQi
216 Stars 49 Forks 2 Commits 13 Opened issues

Description

Code for ECCV2018 - Learning Human-Object Interactions by Graph Parsing Neural Networks.

Services available

!
?

Need anything else?

Contributors list

# 87,015
Python
mesh
constru...
2 commits

ECCV2018 - Learning Human-Object Interactions by Graph Parsing Neural Networks

Introduction

The algorithm is described in the ECCV 2018 paper: Learning Human-Object Interactions by Graph Parsing Neural Networks. In this work, we introduce the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being differentiable end-to-end. teaser


Environment and installation

This repository is developed under CUDA8.0 and pytorch3.1 in python2.7. Early versions of pytorch can be found here. The required python packages can be installed by:

bash
pip install http://download.pytorch.org/whl/cu80/torch-0.3.1-cp27-cp27mu-linux_x86_64.whl
pip install -r requirements.txt

Download the pre-trained model and features

  • Download the entire
    tmp
    folder from this google drive and put under the root folder of the repository.
  • Unzip the
    hico_data_background_49.zip
    file under
    gpnn/tmp/hico/processed
    .
  • The file structure should look like:
    /gpnn
    /src
    /python
    /tmp
    /cad120
    /hico
      /processed
        /hico_data_background_49
    /checkpoints
    /results
    

Running the code

  • Change the
    self.project_root
    in
    config.py
    to your own path of the repository.
  • Run the following files for experiments:
    hico.py
    human-object interaction detection for HICO-DET dataset.
    cad120.py
    : detection for the CAD120 dataset.
    cad120_prediction.py
    : prediction for the CAD120 dataset.

If you want to train the model from scratch, just change the default epoch number from 0 to 100, and rename the pre-trained models. Running the above files should start the training.

Evaluation

The experiment results are provided in

tmp/results/
. The benchmarking tool for the DET-HICO datset can be found here.

Citation

If you find this code useful, please cite our work with the following bibtex:

@inproceedings{qi2018learning,
    title={Learning Human-Object Interactions by Graph Parsing Neural Networks},
    author={Qi, Siyuan and Wang, Wenguan and Jia, Baoxiong and Shen, Jianbing and Zhu, Song-Chun},
    booktitle={European Conference on Computer Vision (ECCV)},
    year={2018}
}

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.