Skip to content

A PyTorch implementation of the paper "Training Neural Networks Using Features Replay"

Notifications You must be signed in to change notification settings

slowbull/FeaturesReplay

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Introduction

This repository is the PyTorch code for the paper Training Neural Networks Using Features Replay " by Zhouyuan Huo, Bin Gu and Huang, Heng, NeurIPS 2018 Spotlight.

For any question or suggestions, feel free to contact zhouyuan.huo@pitt.edu

Dependencies

  • Python 3.6.2 (Anaconda)
  • PyTorch 0.3.1
  • CUDA 8.0

Run

Clone and cd into the repo directory, run:

sh run.sh

Citation

@inproceedings{huo2018training,
  title={Training neural networks using features replay},
  author={Huo, Zhouyuan and Gu, Bin and Huang, Heng},
  booktitle={Advances in Neural Information Processing Systems},
  pages={6659--6668},
  year={2018}
}

About

A PyTorch implementation of the paper "Training Neural Networks Using Features Replay"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published