Skip to content
Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks"
Python
Branch: master
Clone or download
Latest commit 3503e68 Nov 22, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
keras fix: inital_decay typo changed to initial_decay Jan 28, 2017
lasagne readme Dec 3, 2016
tensorflow first commit Dec 3, 2016
LICENSE.md first commit Dec 3, 2016
README.md update README with repo status Nov 21, 2018

README.md

Status: Archive (code is provided as-is, no updates expected)

Weight Normalization

This repo contains example code for Weight Normalization, as described in the following paper:

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks, by Tim Salimans, and Diederik P. Kingma.

  • The folder 'lasagne' contains code using the Lasagne package for Theano. This code was used to run the CIFAR-10 experiments in the paper.
  • The folder 'tensorflow' contains a single nn.py file with a direct implementation copied from our PixelCNN++ repository.
  • The folder 'keras' contains example code for use with the Keras package.

Citation

If you find this code useful please cite us in your work:

@inproceedings{Salimans2016WeightNorm,
  title={Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks},
  author={Tim Salimans and Diederik P. Kingma},
  booktitle={Neural Information Processing Systems 2016},
  year={2016}
}
You can’t perform that action at this time.