https://github.com/podgorskiy/vae

Example of vanilla VAE for face image generation at resolution 128x128 using pytorch.
https://github.com/podgorskiy/vae

autoencoder celeba celeba-dataset deep-learning deep-neural-networks deeplearning faces pytorch vae variational-autoencoder

Last synced: 7 days ago
JSON representation

Example of vanilla VAE for face image generation at resolution 128x128 using pytorch.

Host: GitHub
URL: https://github.com/podgorskiy/vae
Owner: podgorskiy
Created: 2019-03-08T19:55:42.000Z (over 6 years ago)
Default Branch: master
Last Pushed: 2019-03-11T02:18:43.000Z (over 6 years ago)
Last Synced: 2025-05-01T03:36:31.831Z (about 2 months ago)
Topics: autoencoder, celeba, celeba-dataset, deep-learning, deep-neural-networks, deeplearning, faces, pytorch, vae, variational-autoencoder
Language: Python
Homepage:
Size: 5.17 MB
Stars: 73
Watchers: 3
Forks: 13
Open Issues: 3
Metadata Files:
- Readme: README.md

README

# Variational Autoencoder
Example of vanilla VAE for face image generation at resolution 128x128.

Auto-Encoding Variational Bayes: https://arxiv.org/abs/1312.6114

Generation:

Original Faces vs. Reconstructed Faces:

## How to Run
You need to have pytorch >= v0.4.1 and cuda/cuDNN drivers installed.

To install requirements:

```python
pip install -r requirements.txt
```

To download and prepare dataset:
```python
python prepare_celeba.py
```

To train:
```python
python VAE.py
```