Giter VIP home page Giter VIP logo

triple-wins's Introduction

Triple-Wins

[ICLR 20] Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference

Prerequisite

This code requires Pytorch 1.1.0

BibTeX

@inproceedings{tkhu2019triplewins,
author={Ting{-}Kuei Hu and Tianlong Chen and Haotao Wang and Zhangyang Wang},
title ={Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference},
booktitle={ICLR},
year = {2020},
}

STATUS

upload mnist code -- 2020/03/17

TODOS

upload mnist pretrained model ( Done on 10/01/2021)

upload cifar code ( Done on 10/01/2021)

upload cifar pretrained model ( Done on 10/01/2021)

triple-wins's People

Contributors

tianlong-chen avatar ting-kuei avatar tingkuei avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

triple-wins's Issues

Max Average Approach diverges in cifar10

Hello, I want to use your code for my experiment, but I cannot train ResNet and MobileNet with your max average approach.

I discovered that a model(ResNet or MobileNet) diverges when I train a model with Max Average Approach using your code.

I think that there are some experiment details what you did not mention in your paper such as batch size or warm-up in ResNet experiments.

I want to know specific experiment details. Can you tell me more specific experiments details?

Also, in MobileNet, there are 7 branches in your code although 3 branches in your paper.

I also want to use MobileNet v2 with 3 branches version code.
Can you upload your 3 branches version code if you allow to open to the public?

Thank you

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.