https://github.com/edouardoyallon/deep_separation_contraction

This is the code for the CVPR17 paper "Building a Regular Decision Boundary with Deep Networks"
https://github.com/edouardoyallon/deep_separation_contraction

Last synced: 23 days ago
JSON representation

This is the code for the CVPR17 paper "Building a Regular Decision Boundary with Deep Networks"

• Host: GitHub
• URL: https://github.com/edouardoyallon/deep_separation_contraction
• Owner: edouardoyallon
• Created: 2016-11-15T17:03:13.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2017-03-06T08:35:51.000Z (almost 8 years ago)
• Last Synced: 2025-01-10T21:11:28.594Z (24 days ago)
• Language: Python
• Homepage: http://www.di.ens.fr/~oyallon/
• Size: 17.6 KB
• Stars: 6
• Watchers: 5
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Building a Regular Classification Boundary with Deep Networks

This is the code for the CVPR17 paper  "Building a Regular Classification Boundary with Deep Networks" by Edouard Oyallon. A large part of the code is inspired from https://github.com/bgshih/tf_resnet_cifar yet it has been modified a lot.

To run all the experiments and obtain the figure of the paper, you can simply do:

bash script_nonlinearity_alpha.bash

python build_figure_paper.py

The best accuracy on CIFAR10 should be 95.4, and on CIFAR100 it should be 79.6, with n_channel equal to 512, alpha=1.0.

# Acknowledgement

Code modified by Edouard Oyallon - Team DATA ENS, 2016