is0383kk/Dirichlet-VAE
Dirichlet-Variational Auto-Encoder by PyTorch
This project offers a specialized image compression and generation technique. It takes image data as input and produces compressed representations that capture key visual characteristics, along with the ability to generate new, similar images based on these representations. It's designed for researchers or machine learning engineers working on advanced image processing tasks who need to explore different probabilistic models for latent space representations.
No commits in the last 6 months.
Use this if you are a researcher in machine learning or computer vision and need to experiment with Variational Autoencoders that use a Dirichlet distribution for their latent variables when working with image datasets.
Not ideal if you are looking for an off-the-shelf image compression solution or a simple generative model for general use, as this is a research-oriented implementation.
Stars
24
Forks
5
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/is0383kk/Dirichlet-VAE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
EdoardoBotta/RQ-VAE-Recommender
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with...
is0383kk/SymbolEmergence-VAE-GMM
Symbol emergence using Variational Auto-Encoder and Gaussian Mixture Model...
Bhavik-Ardeshna/pytorch-VAE
Variational Autoencoder and a Disentangled version (beta-VAE) implementation in PyTorch-Lightning
farhad-dalirani/Controllable-Face-Generation-VAE
A controllable generative model using a Convolutional Variational Autoencoder (VAE) with GUI to...
EdoardoBotta/Gaussian-Mixture-VAE
[Pytorch] Minimal implementation of a Variational Autoencoder (VAE) with Categorical Latent...