changliu00/cygen
Codes for CyGen, the novel generative modeling framework proposed in "On the Generative Utility of Cyclic Conditionals" (NeurIPS-21)
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.
Stars
44
Forks
6
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
junyanz/CycleGAN
Software that can generate photos from paintings, turn horses into zebras, perform style...
aleju/face-generator
Generate human faces with neural networks
junyanz/iGAN
Interactive Image Generation via Generative Adversarial Networks
HyperGAN/HyperGAN
Composable GAN framework with api and user interface
cs-chan/ArtGAN
ArtGAN + WikiArt: This work presents a series of new approaches to improve GAN for conditional...