Skip to content

Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

License

Notifications You must be signed in to change notification settings

cgraber/cvpr_dNRI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Code accompanying "Dynamic Neural Relational Inference"

This codebase accompanies the paper "Dynamic Neural Relational Inference" from CVPR 2020.

This code was written using the following packages:

  • PyTorch 1.2.0
  • numpy 1.16.4
  • transforms3d 0.3.1 (For Motion Capture data processing)
  • pandas (for InD data processing)

To run this code, you should pip install it in editable mode. This can be done using the following command:

pip install -e ./

Scripts train models can be found in the run_scripts directory.

Datasets:

Attribution: Some portions of this code are based on the code for the paper "Neural Relational Inference for Interacting Systems." This code can be found at https://github.com/ethanfetaya/NRI

If you use this code or this model in your work, please cite us:

@inproceedings{dNRI,
  title={Dynamic Neural Relational Inference},
  author={Graber, Colin and Schwing, Alexander},
  booktitle={The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
}

About

Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published