Giter VIP home page Giter VIP logo

vae's Introduction

VAE

This repository is for sharing the scripts of VAE.

Latent space of the test-set data.

Description

You can train MNIST with any number of latent variable dimensions, and visualize the latent space from multiple perspectives.

Requirement

  • Python: 3.7
  • fire: 0.4

Usage

You can use the following command to train and visualize VAE.

python main.py main --z_dim [The dimensions of latent variables]

You can start tensorboard with the following command. Note that The default URL is http://localhost:6006/.

tensorboard --logdir ./logs

Network

The configuration of VAE is shown as below.

The configuration of VAE.

Output

You can get the following images.

Reconstruction

Reconstructions of the test-set data.

Mappings of the latent space

Mappings of the latent space in the test-set data.

Generation from lattice points

Artificially generated lattice points.


Reconstructions generated from lattice points.

Walkthrough

Four-direction-walkings at a constant speed in potential space.


Reconstructions obtained from a walkthrough of the latent space.

vae's People

Contributors

beginaid avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

vae's Issues

lattice_point and walkthrough doesn't work except z_dim=2

It seems that lattice_point and walkthrough just works when z_dim=2.
For example, z_dim=10, following error rises.

python3\lib\site-packages\torch\nn\functional.py", line 1692, in linear
output = input.matmul(weight.t())
RuntimeError: mat1 and mat2 shapes cannot be multiplied (625x2 and 10x200)

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.