# bojone/vae

a simple vae and cvae from keras

Repository: https://github.com/bojone/vae
Canonical: https://ross.abutalabs.com/products/vae
Language: Python
License Family: other
Last push: 2021-05-18T04:34:24+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3090, "days_push": 1933, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1389, forks 372 (observed 2026-08-28T04:04:35.353485+00:00)

## What it is
A collection of simple Keras implementations of variational autoencoders (VAE) and conditional VAEs (CVAE), with example results on datasets like CelebA. It serves as reference/demo code accompanying blog posts on the author's site.

## Use cases
- learn how to implement a vae in keras
- example code for conditional vae
- generate faces with a vae on celeba
- understand vae clustering with mnist
- starting point for building generative autoencoder models

## When to choose
- you want minimal, readable VAE/CVAE reference implementations in Keras
- you are following the author's blog tutorials on VAEs
- you need a quick baseline for autoencoder experiments on older TensorFlow/Keras stacks

## When to avoid
- you need a maintained, production-ready generative modeling library
- you use modern TensorFlow 2.x or PyTorch and need up-to-date APIs
- you need a license permitting redistribution

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, data-visualization
- domain: deep-learning, machine-learning, image-processing
- platform: python
- tags: variational-autoencoder, keras, cvae, example-code, generative-models

## Member repositories
- bojone/vae (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:35.353485+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:42.087500+00:00, confidence not recorded.
  - readme: https://github.com/bojone/vae (fetched 2026-08-28T04:04:35.353485+00:00, sha e4d36d6f8eb2)
- Data as of 2026-08-30T08:39:29.467469+00:00.