cheind/autoregressive
:kiwi_fruit: Autoregressive Models in PyTorch.
This project helps machine learning researchers and practitioners explore and apply WaveNet-like autoregressive models. You can input sequential data, such as time-series or images treated as sequences, to generate new data samples or make predictions. The project provides code and pre-trained models for tasks like forecasting periodic signals or classifying and generating handwritten digits.
No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer interested in experimenting with advanced autoregressive models for sequential data generation, prediction, or classification tasks.
Not ideal if you need a plug-and-play solution for common time-series forecasting or image generation without delving into model architecture or PyTorch.
Stars
81
Forks
4
Language
Python
License
MIT
Last pushed
Apr 03, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cheind/autoregressive"
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)