nnormandin/Conditional_VAE
conditional variational autoencoder written in Keras [not actively maintained]
This project helps machine learning practitioners explore and understand how conditional variational autoencoders (CVAEs) work. It takes in images (specifically handwritten digits like those from MNIST) and their corresponding labels, then learns to generate new images of those digits. Researchers and students in deep learning can use this to see how a CVAE can generate specific types of data based on conditions.
No commits in the last 6 months.
Use this if you are a machine learning researcher or student who wants to understand and implement conditional variational autoencoders for generative modeling tasks, especially with image data.
Not ideal if you need a production-ready CVAE implementation or a tool for general image generation beyond simple digit examples.
Stars
97
Forks
46
Language
Jupyter Notebook
License
—
Last pushed
Oct 02, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nnormandin/Conditional_VAE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)