niazangels/vae-pokedex
The companion code for How to Autoencode your Pokemon
This project helps you understand how a computer can learn to compress and recreate images, specifically using Pokémon sprites as an example. You'll input a collection of Pokémon images, and the system will show you how it learns to represent them more efficiently and even generate new, similar sprites. This is ideal for students or enthusiasts curious about machine learning's creative applications, especially in digital art or game asset creation.
No commits in the last 6 months.
Use this if you want a practical, visual demonstration of how autoencoders work with image data, without needing to be a deep learning expert.
Not ideal if you're looking for a tool to generate production-ready game assets or to perform advanced image analysis.
Stars
80
Forks
22
Language
Jupyter Notebook
License
—
Last pushed
Jul 17, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/niazangels/vae-pokedex"
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)