Coder Social home page Coder Social logo

Comments (4)

SharifAmit avatar SharifAmit commented on June 11, 2024

Hi

You can check with holdout test set and using the eval.py file, We only evaluate after the third stage ( after training for 100 epochs 3 times).

https://github.com/SharifAmit/RVGAN/blob/master/eval.py

Hope this answers your question.

from rvgan.

icyclv avatar icyclv commented on June 11, 2024

Thank you for your reply.
I have a question that will the results differ between the two versions(tf2.0 and tf2.6)?Because I have trained the model on tf26 branch,but the f1 score is around 0.75.

from rvgan.

SharifAmit avatar SharifAmit commented on June 11, 2024

Hi,

I highly recommend using tf 2.0. As the original model, loss implementation and training was carried out in that version. tf 2.6 was implemented solely for the following issue (Link: #8) and we have not formally verified the training or evaluation on that.

Hope this helps.

Thanks

from rvgan.

icyclv avatar icyclv commented on June 11, 2024

Thanks for your work!

from rvgan.

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.