dpernes/vae

Customisable Variational Autoencoder in PyTorch

26
/ 100
Experimental

This tool helps machine learning engineers and researchers explore and understand complex datasets by compressing data into a simpler, underlying representation and then reconstructing it. You input raw data, like images, and it outputs a compressed version as well as newly generated, similar data points. It's ideal for those working on data generation, anomaly detection, or dimensionality reduction tasks.

No commits in the last 6 months.

Use this if you need a flexible way to customize and train a Variational Autoencoder model for tasks like generating new data samples or reducing the complexity of your datasets.

Not ideal if you require a different decoder architecture than the transposed version of your encoder, as this implementation imposes that constraint.

data-generation dimensionality-reduction machine-learning-research image-processing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Python

License

Last pushed

Oct 31, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dpernes/vae"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.