Robotmurlock/VariationalAutoEncoder

Implementation of the Auto-Encoding Variational Bayes paper in Pytorch with detailed explanation.

20
/ 100
Experimental

This project provides an implementation and explanation of a Variational Autoencoder (VAE), a type of generative model that learns from your existing data to create new, similar data. You input a dataset, and the model learns to compress it into a 'latent space' and then reconstruct it, enabling the generation of novel data points. It is designed for practitioners working with high-dimensional datasets who need to generate new samples or perform advanced dimensionality reduction.

No commits in the last 6 months.

Use this if you need to generate new, synthetic data samples that are statistically similar to an existing dataset, or if you require a non-linear method for reducing the dimensionality of complex data for tasks like visualization.

Not ideal if you only need basic linear dimensionality reduction (like PCA) or if your primary goal is classification rather than data generation or complex representation learning.

data-generation dimensionality-reduction unsupervised-learning data-synthesis image-generation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Jupyter Notebook

License

Last pushed

Aug 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Robotmurlock/VariationalAutoEncoder"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.