Giter VIP home page Giter VIP logo

Comments (2)

nmgzjf avatar nmgzjf commented on September 25, 2024 1

@clu2033 @zo7 I guess clu2033 use early_stopping in a merge model. It seems that Keras does not provide val_acc and val_loss in merge model, so the monitor only can be set to acc or loss. So if merge model is adopted, please modify the value of monitor.

from deconvfaces.

somewacko avatar somewacko commented on September 25, 2024

Hmm that's odd...

  1. It says it found 0 instances and 0 identities -- which dataset are you using? This only supports RaFD and Yale Faces (the latter you need to give a flag when you run it, see which with python3 faces.py train -h)
  2. Which version of Keras are you using? It looks like the model compiled without monitoring the loss (which it should by default), but the callbacks I use to save the model and stop it early need it to work.

from deconvfaces.

Related Issues (12)

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.