nathanhubens/Autoencoders
Implementation of simple autoencoders networks with Keras
This project helps you understand how neural networks can learn to compress data and then reconstruct it. You provide a dataset, and it shows you how to build models that can reduce the data's complexity while retaining essential information. This is useful for anyone exploring data compression, feature learning, or anomaly detection techniques.
264 stars. No commits in the last 6 months.
Use this if you are an AI student or researcher looking to grasp the fundamental concepts and various implementations of autoencoders.
Not ideal if you need a production-ready data compression solution or a tool for immediate, complex data analysis without understanding the underlying neural network architecture.
Stars
264
Forks
94
Language
Jupyter Notebook
License
MIT
Last pushed
Aug 04, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nathanhubens/Autoencoders"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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)