Code Monkey home page Code Monkey logo

damnets's Introduction

Implementation of the paper Domain-Adaptive Multibranch Networks using Pytorch

Currently only LeNet based Multibranch Network has been implemented

General Architecture

Multibranch LeNet

How to use?

  1. Open the terminal
  2. Type git clone https://github.com/PanPapag/DAMNets.git to clone the repository to your local machine
  3. Type pip install -r requirements.txt
  4. Type python main.py --help to view possible options
  5. Type python main.py to run the app

TODOs

  1. Add more available datasets
  2. Add model checkpoint saving option, so as to load a pretrained model and test.
  3. Build the other DAMNets

Feel free to contribute 😃

License

This project is licensed under the MIT License.

MIT © PanPapag

damnets's People

Contributors

panpapag avatar

Stargazers

avatar Zhipeng Zhou avatar avatar avatar Jiangangyang_CAS avatar avatar Yongxing Dai avatar avatar jbkim avatar avatar IronMan avatar Andreas Spanopoulos avatar Nick Galanis avatar Vassilis Sioros avatar

Watchers

James Cloos avatar avatar avatar IronMan avatar

Forkers

lliai yys-polaris weix-liu hamedamz

damnets's Issues

SVHNet

Dear author：
Can you provide a SVHNet-based Multibranch Network?

Hello, I have a question about the test

An error occurred during the test phase while I was running the program.
TypeError: forward() missing 1 required positional argument: 'plasticity'
I found that there was no input 'plasticity' parameter during the test phase,But the network "forward" has this parameter.
I tried to add this parameter to the test, but got poor classification results.
Source Accuracy: 54477/60000 (90.7950%)
Target Accuracy: 20929/60000 (34.8817%)
Domain Accuracy: 70938/120000 (59.1150%)
What is the reason？
Is it because I've been using the epoch less? (The results above were 20 times after the epoch and found that accuracy barely changed again). Or was it because I added the 'plasticity' that caused the accuracy of the tests to drop.
Please answer my question, 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.