changliu00/cygen

Codes for CyGen, the novel generative modeling framework proposed in "On the Generative Utility of Cyclic Conditionals" (NeurIPS-21)

37
/ 100
Emerging

This project offers a novel way for machine learning researchers and practitioners to build generative models. It takes in raw data (like images) and outputs high-quality synthetic data, along with well-structured representations of the original data. This helps in tasks requiring realistic data generation or understanding underlying data patterns without needing to explicitly define a prior distribution.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner working on generative models and want to generate high-quality synthetic data or learn effective data representations without specifying a prior distribution.

Not ideal if you are a beginner looking for a simple, out-of-the-box data augmentation tool, or if your primary goal is not related to generative modeling research.

generative-modeling synthetic-data-generation representation-learning machine-learning-research unsupervised-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

44

Forks

6

Language

Python

License

MIT

Last pushed

Apr 18, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/changliu00/cygen"

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