https://github.com/gazeux33/variational-autoencoders
The aim is to create a VAEs in with PyTorch to create synthetic data
https://github.com/gazeux33/variational-autoencoders
fashion-mnist image-generation pytorch variational-autoencoder
Last synced: 3 months ago
JSON representation
The aim is to create a VAEs in with PyTorch to create synthetic data
- Host: GitHub
- URL: https://github.com/gazeux33/variational-autoencoders
- Owner: Gazeux33
- Created: 2024-04-25T21:16:18.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-05-04T15:05:18.000Z (about 1 year ago)
- Last Synced: 2025-02-09T14:19:42.224Z (5 months ago)
- Topics: fashion-mnist, image-generation, pytorch, variational-autoencoder
- Language: Jupyter Notebook
- Homepage:
- Size: 407 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Variational-Autoencoders(VAEs)
## The project
This project is an implementation of Variational Autoencoders (VAEs) using PyTorch. VAEs are generative models that learn to represent high-dimensional data in a lower-dimensional latent space and can generate new data samples similar to the training data.
## Features
+ Implementation of a Variational Autoencoder architecture.
+ Training pipeline for learning latent representations.
+ Generation of new data samples from the learned latent space.
## What is a VAE ?
## Technical specifications
| Property | Value |
|----------------|---------------|
| Device | MAC M2 |
| Training Time | ~20 min |
| Epochs | 5 |
| Training Data | FashionMNIST |
| Framework | PyTorch |
| Learning rate | 0.001 |
|Z_DIM |10 |
|BATCH_SIZE |32 |
## Examples of constructions and reconstructions
## Examples of images extracted directly from latent space (fictives images)
