Giter Site home page Giter Site logo

cuai / neural-manifold-ordinary-differential-equations Goto Github PK

View Code? Open in Web Editor NEW
109.0 12.0 14.0 23 KB

[NeurIPS 2020] Neural Manifold Ordinary Differential Equations (https://arxiv.org/abs/2006.10254)

Python 100.00%
machine-learning generative-models neural-manifold-odes neurips-2020

neural-manifold-ordinary-differential-equations's People

Contributors

cptq avatar isaykatsman avatar louaaron 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  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

neural-manifold-ordinary-differential-equations's Issues

hyperboloid works after minor fix, but sphere is not working

Hyperboloid: The hyperboloid code throws an error due to the "loc" property being defined after the parent init is called.
By putting https://github.com/CUAI/Neural-Manifold-Ordinary-Differential-Equations/blob/master/distributions/wnormal.py l.14 (the parent init call) to the end, we can solve that. After that the plots from the README can be constructed.

Sphere: The sphere does not seem to work at all. I am getting either black visualization or azimuthally symmetric ones.
Are there any crucial commits missing? It woul be nice to be able to reproduce the plots on the README, right now it is not possible.

Using pytorch 1.9 and the latest torchdiffeq.

How can I work "sphere" well?

The sphere does not seem to work at all. I am getting either black visualization or azimuthally symmetric ones.
Are there any crucial commits missing? It woul be nice to be able to reproduce the plots on the README, right now it is not possible.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.