https://github.com/yuanx749/vae-mixin-pytorch

Variational autoencoders as mixins.
https://github.com/yuanx749/vae-mixin-pytorch

project pytorch vae

Last synced: 5 days ago
JSON representation

Variational autoencoders as mixins.

• Host: GitHub
• URL: https://github.com/yuanx749/vae-mixin-pytorch
• Owner: yuanx749
• License: mit
• Created: 2023-02-27T11:35:46.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-14T13:47:26.000Z (about 1 year ago)
• Last Synced: 2023-11-14T16:46:43.459Z (about 1 year ago)
• Topics: project, pytorch, vae
• Language: Python
• Homepage: https://yuanx749.github.io/vae-mixin-pytorch/
• Size: 15.6 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# vae-mixin-pytorch

Variational autoencoders as mixins.

This repo contains implementation of variational autoencoder (VAE) and variants in PyTorch as mixin classes, which can be reused and composed in your customized modules.

## Usage

Check the docs [here](https://yuanx749.github.io/vae-mixin-pytorch/).

An example using simple encoder and decoder on the MNIST dataset is in [example.py](https://github.com/yuanx749/vae-mixin-pytorch/blob/main/example.py).

```{note}

Mixin is a term in object-oriented programming.

```

## Notes

Implemented VAEs:

- VAE

- beta-VAE

- InfoVAE

- DIP-VAE

- $\beta$-TCVAE

- VQ-VAE

```{note}

Losses are averaged across samples, and summed along each latent vector in a minibatch.

```