Skip to content

Tensorflow Implementation of Visualization Regularizers for Neural Network based Image Recognition

Notifications You must be signed in to change notification settings

cvikasreddy/VisReg

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 

Repository files navigation

VisReg

Implementation of the visualization regularizer (https://arxiv.org/abs/1604.02646) for neural networks trained on image tasks.

Instructions

Pre-requisites

The following python packages are required to be installed:

File organization

  • Data is located in cifar/data and mnist/data.
  • Logs generated by tensorflow summarywriter is stored in cifar/logs and mnist/logs.
  • Models are stored in cifar/models and mnist/models.

Training

The file mnist/train.py and cifar/train.py can be used to train the appropriate model by changing the parameters beta, gamma, theta for L2, VR2, VR1 regularizer coffecients.

About

Tensorflow Implementation of Visualization Regularizers for Neural Network based Image Recognition

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published