Giter Club home page Giter Club logo

Comments (2)

mrT23 avatar mrT23 commented on June 19, 2024 1

I don't think your question relates to ASL.
you can train with ASL without EMA.
on multi-label problems, we found that EMA helps a lot (for any loss function).

so my first recommendation is to try EMA +cross-entropy on your problem, and see if results are less dependent on the selected checkpoints. my strong guess - no.

i think that 'checkpoint averaging'+'no ema' will be somewhat equivalent to EMA. with EMA, i don't think you get a big benefit from 'checkpoint averaging'.

from asl.

pgsrv avatar pgsrv commented on June 19, 2024

Thank you very much!

from asl.

Related Issues (20)

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.