https://github.com/timbmg/vae-cvae-mnist

Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch
https://github.com/timbmg/vae-cvae-mnist

cvae deep-learning latent-variable-models mnist pytorch vae variational-autoencoder

Last synced: 12 days ago
JSON representation

Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch

• Host: GitHub
• URL: https://github.com/timbmg/vae-cvae-mnist
• Owner: timbmg
• Created: 2018-02-26T12:54:18.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2024-07-25T10:48:03.000Z (4 months ago)
• Last Synced: 2024-10-12T18:31:05.365Z (about 1 month ago)
• Topics: cvae, deep-learning, latent-variable-models, mnist, pytorch, vae, variational-autoencoder
• Language: Python
• Homepage:
• Size: 1.11 MB
• Stars: 579
• Watchers: 8
• Forks: 104
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Variational Autoencoder & Conditional Variational Autoenoder on MNIST

VAE paper: [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114)

CVAE paper: [Semi-supervised Learning with Deep Generative Models](https://proceedings.neurips.cc/paper/2014/hash/d523773c6b194f37b938d340d5d02232-Abstract.html)

---

In order to run _conditional_ variational autoencoder, add `--conditional` to the the command. Check out the other commandline options in the code for hyperparameter settings (like learning rate, batch size, encoder/decoder layer depth and size).

---

## Results

All plots obtained after 10 epochs of training. Hyperparameters accordning to default settings in the code; not tuned.

### z ~ q(z|x) and q(z|x,c)

The modeled latent distribution after 10 epochs and 100 samples per digit.

VAE | CVAE

--- | --- 

 | 

### p(x|z) and p(x|z,c)

Randomly sampled z, and their output. For CVAE, each c has been given as input once.

VAE | CVAE

--- | --- 

 |