Skip to content

Latest commit

 

History

History
97 lines (84 loc) · 2.42 KB

README.md

File metadata and controls

97 lines (84 loc) · 2.42 KB

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.