Coder Social home page Coder Social logo

donydchen / fmpn-fer Goto Github PK

View Code? Open in Web Editor NEW
99.0 99.0 23.0 1.97 MB

😁[VCIP'19 Oral] Official PyTorch Implementation of Facial Motion Prior Networks for Facial Expression Recognition

License: MIT License

Python 100.00%
expression facial-expression-recognition pytorch vcip-2019

fmpn-fer's People

Contributors

donydchen 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  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  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

fmpn-fer's Issues

Neutral label

Hi, I wonder how to deal with the training data with neutral label.

Pre-trained model files

Hey, I was wondering if the pre-trained models are available and if so where I could find them?

Setting the number of epoch in trainning

Hello, I have stuck in set epoch of pre train. I was to reduce the epoch not 300, because my laptop is really hot while running. Hope you can show me where to fix that. Thank you so much.

Problem of visdom

Hello, I have some problem with visdom in the below picture.
image

There is not something like diagram or graph,...

How I can see the output of the train? Really need help, thank you so much.

In Face generation network , average difference face is not being used in code?

The paper and the code contradicts . Paper says "Note that the learning of FMG is
guided by pseudo ground truth masks, which are the average differences between neutral faces and their corresponding expressive faces" but the training part of ResFaceGenNet i didnt find usage of average diff face so please clarify this confusion.

Can't access connection in Google Colab

Hello,
I have some problem with the first script and here are the traceback.
image

I wonder that did I run in google colab is right? Or I have to run local in pycharm or jupyter notebook?

Train with affectnet

Hi. Thank you for your awesome work.
How can I generate masks for training with AffectNet?

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.