Git Product home page Git Product logo

froggan's Introduction

Dataset link: https://github.com/jonshamir/frog-dataset

Video Demo: 2 - Timelapse of DCGAN learning to make frogs

Extract the images generated during training from the tensorboard logs and make video: dev/tb_images.py

Findings:

  • model.py L89 - reducing the discriminator learning rate helps. unclear why
  • dcgan.py - discriminator with spectral_norm
  • dcgan.py - activations that are not piecewise work better. I think it's because there is more gradient signal. ie. GELU and SiLU are better than ReLU
  • train.py - RandomResizedCrop with limited scaling for data augmentation

frog-dataset notes

turtle images
raw/frog-7542
224/frog-5727
64/frog-5727

what is this
224/frog-7662
64/frog-7662

4 frogs
raw/frog-7716

froggan's People

Contributors

lukeasargen avatar

Watchers

avatar

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.